Search

Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs). Strengthening adversarial attacks and uncovering vulnerabilities, especially common issues in VLP models (e.g., high transferable AEs), can stimulate further research on constructing reliable and practical VLP models. A recent work (i.e., Set-level guidance attack) indicates that augmenting image-text pairs to increase AE diversity along the optimization path enhances the transferability of adversarial examples significantly. However, this approach predominantly emphasizes diversity around the online adversarial examples (i.e., AEs in the optimization period), leading to the risk of overfitting the victim model and affecting the transferability. In this study, we posit that the diversity of adversarial examples towards the clean input and online AEs are both pivotal for enhancing transferability across VLP models. Consequently, we propose using diversification along the intersection region of adversarial trajectory to expand the diversity of AEs. To fully leverage the interaction between modalities, we introduce text-guided adversarial example selection during optimization. Furthermore, to further mitigate the potential overfitting, we direct the adversarial text deviating from the last intersection region along the optimization path, rather than adversarial images as in existing methods. Extensive experiments affirm the effectiveness of our method in improving transferability across various VLP models and downstream vision-and-language tasks (e.g., Image-Text Retrieval(ITR), Visual Grounding(VG), Image Captioning(IC)).

Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are easily perceived or defended against. The trade-off between the imperceptibility and adversarial strength leads most point attack methods to inevitably introduce easily detectable outlier points upon a successful attack. Another promising strategy, shape-based attack, can effectively eliminate outliers, but existing methods often suffer significant reductions in imperceptibility due to irrational deformations. We find that concealing deformation perturbations in areas insensitive to human eyes can achieve a better trade-off between imperceptibility and adversarial strength, specifically in parts of the object surface that are complex and exhibit drastic curvature changes. Therefore, we propose a novel shape-based adversarial attack method, HiT-ADV, which initially conducts a two-stage search for attack regions based on saliency and imperceptibility scores, and then adds deformation perturbations in each attack region using Gaussian kernel functions. Additionally, HiT-ADV is extendable to physical attack. We propose that by employing benign resampling and benign rigid transformations, we can further enhance physical adversarial strength with little sacrifice to imperceptibility. Extensive experiments have validated the superiority of our method in terms of adversarial and imperceptible properties in both digital and physical spaces. Our code is avaliable at: https://github.com/TRLou/HiT-ADV., Comment: Accepted by CVPR 2024

The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim to distinguish forged faces from genuine ones and have proven effective in practical applications. However, this paper introduces a novel and previously unrecognized threat in face forgery detection scenarios caused by backdoor attack. By embedding backdoors into models and incorporating specific trigger patterns into the input, attackers can deceive detectors into producing erroneous predictions for forged faces. To achieve this goal, this paper proposes \emph{Poisoned Forgery Face} framework, which enables clean-label backdoor attacks on face forgery detectors. Our approach involves constructing a scalable trigger generator and utilizing a novel convolving process to generate translation-sensitive trigger patterns. Moreover, we employ a relative embedding method based on landmark-based regions to enhance the stealthiness of the poisoned samples. Consequently, detectors trained on our poisoned samples are embedded with backdoors. Notably, our approach surpasses SoTA backdoor baselines with a significant improvement in attack success rate (+16.39\% BD-AUC) and reduction in visibility (-12.65\% $L_\infty$). Furthermore, our attack exhibits promising performance against backdoor defenses. We anticipate that this paper will draw greater attention to the potential threats posed by backdoor attacks in face forgery detection scenarios. Our codes will be made available at \url{https://github.com/JWLiang007/PFF}, Comment: ICLR 2024 Spotlight

In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving. However, their robustness against common weather corruption such as fog, rain, snow, and sunlight in the intricate physical world remains underexplored. In this paper, we evaluate the robustness of fusion models from the perspective of fusion strategies on the corrupted dataset. Based on the evaluation, we further propose a concise yet practical fusion strategy to enhance the robustness of the fusion models, namely flexibly weighted fusing features from LiDAR and camera sources to adapt to varying weather scenarios. Experiments conducted on four types of fusion models, each with two distinct lightweight implementations, confirm the broad applicability and effectiveness of the approach., Comment: 17 pages

Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. However, they face challenges of being maliciously exploited to generate harmful or sensitive images by appending a specific suffix to the original prompt. Existing works mainly focus on using single-modal information to conduct attacks, which fails to utilize multi-modal features and results in less than satisfactory performance. Integrating multi-modal priors (MMP), i.e. both text and image features, we propose a targeted attack method named MMP-Attack in this work. Specifically, the goal of MMP-Attack is to add a target object into the image content while simultaneously removing the original object. The MMP-Attack shows a notable advantage over existing works with superior universality and transferability, which can effectively attack commercial text-to-image (T2I) models such as DALL-E 3. To the best of our knowledge, this marks the first successful attempt of transfer-based attack to commercial T2I models. Our code is publicly available at \url{https://github.com/ydc123/MMP-Attack}., Comment: 10 figures

Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed I-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG.

The widespread use of diffusion methods enables the creation of highly realistic images on demand, thereby posing significant risks to the integrity and safety of online information and highlighting the necessity of DeepFake detection. Our analysis of features extracted by traditional image encoders reveals that both low-level and high-level features offer distinct advantages in identifying DeepFake images produced by various diffusion methods. Inspired by this finding, we aim to develop an effective representation that captures both low-level and high-level features to detect diffusion-based DeepFakes. To address the problem, we propose a text modality-oriented feature extraction method, termed TOFE. Specifically, for a given target image, the representation we discovered is a corresponding text embedding that can guide the generation of the target image with a specific text-to-image model. Experiments conducted across ten diffusion types demonstrate the efficacy of our proposed method.

With the rising popularity of Large Language Models (LLMs), assessing their trustworthiness through security tasks has gained critical importance. Regarding the new task of universal goal hijacking, previous efforts have concentrated solely on optimization algorithms, overlooking the crucial role of the prompt. To fill this gap, we propose a universal goal hijacking method called POUGH that incorporates semantic-guided prompt processing strategies. Specifically, the method starts with a sampling strategy to select representative prompts from a candidate pool, followed by a ranking strategy that prioritizes the prompts. Once the prompts are organized sequentially, the method employs an iterative optimization algorithm to generate the universal fixed suffix for the prompts. Experiments conducted on four popular LLMs and ten types of target responses verified the effectiveness of our method., Comment: 15 pages

The widespread usage of large-scale multimodal models like CLIP has heightened concerns about the leakage of personally identifiable information (PII). Existing methods for identity inference in CLIP models, i.e., to detect the presence of a person's PII used for training a CLIP model, require querying the model with full PII, including textual descriptions of the person and corresponding images (e.g., the name and the face photo of the person). However, this may lead to potential privacy breach of the image, as it may have not been seen by the target model yet. Additionally, traditional membership inference attacks (MIAs) train shadow models to mimic the behaviors of the target model, which incurs high computational costs, especially for large CLIP models. To address these challenges, we propose a textual unimodal detector (TUNI) in CLIP models, a novel method for ID inference that 1) queries the target model with only text data; and 2) does not require training shadow models. Firstly, we develop a feature extraction algorithm, guided by the CLIP model, to extract features from a text description. TUNI starts with randomly generating textual gibberish that were clearly not utilized for training, and leverages their feature vectors to train a system of anomaly detectors. During inference, the feature vector of each test text is fed into the anomaly detectors to determine if the person's PII is in the training set (abnormal) or not (normal). Moreover, TUNI can be further strengthened integrating real images associated with the tested individuals, if available at the detector. Extensive experiments of TUNI across various CLIP model architectures and datasets demonstrate its superior performance over baselines, albeit with only text data.

Targeted transfer-based attacks involving adversarial examples pose a significant threat to large visual-language models (VLMs). However, the state-of-the-art (SOTA) transfer-based attacks incur high costs due to excessive iteration counts. Furthermore, the generated adversarial examples exhibit pronounced adversarial noise and demonstrate limited efficacy in evading defense methods such as DiffPure. To address these issues, inspired by score matching, we introduce AdvDiffVLM, which utilizes diffusion models to generate natural, unrestricted adversarial examples. Specifically, AdvDiffVLM employs Adaptive Ensemble Gradient Estimation to modify the score during the diffusion model's reverse generation process, ensuring the adversarial examples produced contain natural adversarial semantics and thus possess enhanced transferability. Simultaneously, to enhance the quality of adversarial examples further, we employ the GradCAM-guided Mask method to disperse adversarial semantics throughout the image, rather than concentrating them in a specific area. Experimental results demonstrate that our method achieves a speedup ranging from 10X to 30X compared to existing transfer-based attack methods, while maintaining superior quality of adversarial examples. Additionally, the generated adversarial examples possess strong transferability and exhibit increased robustness against adversarial defense methods. Notably, AdvDiffVLM can successfully attack commercial VLMs, including GPT-4V, in a black-box manner.

Fast adversarial training (FAT) is an efficient method to improve robustness. However, the original FAT suffers from catastrophic overfitting, which dramatically and suddenly reduces robustness after a few training epochs. Although various FAT variants have been proposed to prevent overfitting, they require high training costs. In this paper, we investigate the relationship between adversarial example quality and catastrophic overfitting by comparing the training processes of standard adversarial training and FAT. We find that catastrophic overfitting occurs when the attack success rate of adversarial examples becomes worse. Based on this observation, we propose a positive prior-guided adversarial initialization to prevent overfitting by improving adversarial example quality without extra training costs. This initialization is generated by using high-quality adversarial perturbations from the historical training process. We provide theoretical analysis for the proposed initialization and propose a prior-guided regularization method that boosts the smoothness of the loss function. Additionally, we design a prior-guided ensemble FAT method that averages the different model weights of historical models using different decay rates. Our proposed method, called FGSM-PGK, assembles the prior-guided knowledge, i.e., the prior-guided initialization and model weights, acquired during the historical training process. Evaluations of four datasets demonstrate the superiority of the proposed method.

With the accelerated pace of market-oriented reform, Internet finance has gained a broad and healthy development environment. Existing studies lack consideration of time trends in financial risk, and treating all features equally may lead to inaccurate predictions. To address the above problems, we propose an LSTM model based on sliding window and attention mechanism. The model uses sliding windows to enable the model to effectively exploit the contextual relevance of loan data. And we introduce the attention mechanism into the model, which enables the model to focus on important information. The result on the Lending Club public desensitization dataset shows that our model outperforms ARIMA, SVM, ANN, LSTM, and GRU models.

The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored. We first explore this topic by first evaluating the performance of the existing backdoor attack methods on few-shot learning scenarios. Unlike in standard supervised learning, existing backdoor attack methods failed to perform an effective attack in FSL due to two main issues. Firstly, the model tends to overfit to either benign features or trigger features, causing a tough trade-off between attack success rate and benign accuracy. Secondly, due to the small number of training samples, the dirty label or visible trigger in the support set can be easily detected by victims, which reduces the stealthiness of attacks. It seemed that FSL could survive from backdoor attacks. However, in this paper, we propose the Few-shot Learning Backdoor Attack (FLBA) to show that FSL can still be vulnerable to backdoor attacks. Specifically, we first generate a trigger to maximize the gap between poisoned and benign features. It enables the model to learn both benign and trigger features, which solves the problem of overfitting. To make it more stealthy, we hide the trigger by optimizing two types of imperceptible perturbation, namely attractive and repulsive perturbation, instead of attaching the trigger directly. Once we obtain the perturbations, we can poison all samples in the benign support set into a hidden poisoned support set and fine-tune the model on it. Our method demonstrates a high Attack Success Rate (ASR) in FSL tasks with different few-shot learning paradigms while preserving clean accuracy and maintaining stealthiness. This study reveals that few-shot learning still suffers from backdoor attacks, and its security should be given attention., Comment: AAAI2024

Large Language Models and Multi-Modal LLMs have become pervasive, and so does the importance of their security; yet, modern LLMs are known to be vulnerable to jailbreaking attacks. These attacks can allow malicious users to exploit the models, making the case for effective jailbreak detection mechanisms an essential aspect of maintaining the integrity and trustworthiness of LLM-based applications. However, existing detection works on jailbreak attacks have limitations. Existing post-query-based strategies require target domain knowledge, and pre-query-based methods mainly focus on text-level attacks and fail to meet the increasingly complex multi-modal security requirements placed upon contemporary LLMs. This gap underscores the need for a more comprehensive approach to safeguarding these influential systems. In this work, we propose JailGuard, the first mutation-based jailbreaking detection framework which supports both image and text modalities. Our key observation is that attack queries inherently possess less robustness compared to benign queries. Specifically, to confuse the model, attack queries are usually crafted with well-designed templates or complicate perturbations, leading to a fact that a slight disturbance in input may result in a drastic change in the response. This lack of robustness can be utilized in attack detection. Based on this intuition, we designed and implemented a detection framework comprising 19 different mutators and a divergence-based detection formula. To fully understand the effectiveness of our framework, we built the first multi-modal LLM jailbreaking attack dataset, which has 304 items of data, covering ten types of known jailbreaking attacks on image and text modalities. The evaluation suggests that JailGuard achieves the best detection accuracy of 89.38%/85.42% on image and text inputs, outperforming state-of-the-art defense methods by 15.28%., Comment: 12 pages, 8 figures

Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability adversarial examples is crucial for uncovering VLP models' vulnerabilities in practical scenarios. Recent works have indicated that leveraging data augmentation and image-text modal interactions can enhance the transferability of adversarial examples for VLP models significantly. However, they do not consider the optimal alignment problem between dataaugmented image-text pairs. This oversight leads to adversarial examples that are overly tailored to the source model, thus limiting improvements in transferability. In our research, we first explore the interplay between image sets produced through data augmentation and their corresponding text sets. We find that augmented image samples can align optimally with certain texts while exhibiting less relevance to others. Motivated by this, we propose an Optimal Transport-based Adversarial Attack, dubbed OT-Attack. The proposed method formulates the features of image and text sets as two distinct distributions and employs optimal transport theory to determine the most efficient mapping between them. This optimal mapping informs our generation of adversarial examples to effectively counteract the overfitting issues. Extensive experiments across various network architectures and datasets in image-text matching tasks reveal that our OT-Attack outperforms existing state-of-the-art methods in terms of adversarial transferability.

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in incorrect predictions. In contrast to white-box adversarial attacks, transfer attacks (where the adversary crafts adversarial examples on a white-box model to fool another black-box model) are more reflective of real-world scenarios, thus making them more meaningful for research. By summarizing and analyzing existing research, we identified two factors that can influence the efficacy of transfer attacks on VLP models: inter-modal interaction and data diversity. Based on these insights, we propose a self-augment-based transfer attack method, termed SA-Attack. Specifically, during the generation of adversarial images and adversarial texts, we apply different data augmentation methods to the image modality and text modality, respectively, with the aim of improving the adversarial transferability of the generated adversarial images and texts. Experiments conducted on the FLickr30K and COCO datasets have validated the effectiveness of our method. Our code will be available after this paper is accepted.

Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferability of adversarial examples on semantic segmentation has been largely overlooked. In this paper, we propose an effective two-stage adversarial attack strategy to improve the transferability of adversarial examples on semantic segmentation, dubbed TranSegPGD. Specifically, at the first stage, every pixel in an input image is divided into different branches based on its adversarial property. Different branches are assigned different weights for optimization to improve the adversarial performance of all pixels.We assign high weights to the loss of the hard-to-attack pixels to misclassify all pixels. At the second stage, the pixels are divided into different branches based on their transferable property which is dependent on Kullback-Leibler divergence. Different branches are assigned different weights for optimization to improve the transferability of the adversarial examples. We assign high weights to the loss of the high-transferability pixels to improve the transferability of adversarial examples. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets to demonstrate the effectiveness of the proposed method. The proposed adversarial attack method can achieve state-of-the-art performance.

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has also brought to light a concerning vulnerability: adversarial examples. These crafted inputs, imperceptible to humans, can manipulate machine learning models into making erroneous predictions, raising concerns for safety-critical applications. An intriguing property of this phenomenon is the transferability of adversarial examples, where perturbations crafted for one model can deceive another, often with a different architecture. This intriguing property enables black-box attacks which circumvents the need for detailed knowledge of the target model. This survey explores the landscape of the adversarial transferability of adversarial examples. We categorize existing methodologies to enhance adversarial transferability and discuss the fundamental principles guiding each approach. While the predominant body of research primarily concentrates on image classification, we also extend our discussion to encompass other vision tasks and beyond. Challenges and opportunities are discussed, highlighting the importance of fortifying DNNs against adversarial vulnerabilities in an evolving landscape., Comment: Accepted to Transactions on Machine Learning Research (TMLR)

Adversarial training has shown promise in building robust models against adversarial examples. A major drawback of adversarial training is the computational overhead introduced by the generation of adversarial examples. To overcome this limitation, adversarial training based on single-step attacks has been explored. Previous work improves the single-step adversarial training from different perspectives, e.g., sample initialization, loss regularization, and training strategy. Almost all of them treat the underlying model as a black box. In this work, we propose to exploit the interior building blocks of the model to improve efficiency. Specifically, we propose to dynamically sample lightweight subnetworks as a surrogate model during training. By doing this, both the forward and backward passes can be accelerated for efficient adversarial training. Besides, we provide theoretical analysis to show the model robustness can be improved by the single-step adversarial training with sampled subnetworks. Furthermore, we propose a novel sampling strategy where the sampling varies from layer to layer and from iteration to iteration. Compared with previous methods, our method not only reduces the training cost but also achieves better model robustness. Evaluations on a series of popular datasets demonstrate the effectiveness of the proposed FB-Better. Our code has been released at https://github.com/jiaxiaojunQAQ/FP-Better.

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results in poor robustness performance. Catastrophic Overfitting describes the phenomenon of a sudden and significant decrease in robust accuracy during the training of fast adversarial training. Many effective techniques have been developed to prevent Catastrophic Overfitting and improve the model robustness from different perspectives. However, these techniques adopt inconsistent training settings and require different training costs, i.e, training time and memory costs, leading to unfair comparisons. In this paper, we conduct a comprehensive study of over 10 fast adversarial training methods in terms of adversarial robustness and training costs. We revisit the effectiveness and efficiency of fast adversarial training techniques in preventing Catastrophic Overfitting from the perspective of model local nonlinearity and propose an effective Lipschitz regularization method for fast adversarial training. Furthermore, we explore the effect of data augmentation and weight averaging in fast adversarial training and propose a simple yet effective auto weight averaging method to improve robustness further. By assembling these techniques, we propose a FGSM-based fast adversarial training method equipped with Lipschitz regularization and Auto Weight averaging, abbreviated as FGSM-LAW. Experimental evaluations on four benchmark databases demonstrate the superiority of the proposed method over state-of-the-art fast adversarial training methods and the advanced standard adversarial training methods.

Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achieve consistent efficacy under small volume perturbations and large domain shifts. To address this problem, we propose a novel WavAugment Guided Phoneme Adversarial Training (wapat). wapat use adversarial examples in phoneme space as augmentation to make the model invariant to minor fluctuations in phoneme representation and preserve the performance on clean samples. In addition, wapat utilizes the phoneme representation of augmented samples to guide the generation of adversaries, which helps to find more stable and diverse gradient-directions, resulting in improved generalization. Extensive experiments demonstrate the effectiveness of wapat on End-to-end Speech Challenge Benchmark (ESB). Notably, SpeechLM-wapat outperforms the original model by 6.28% WER reduction on ESB, achieving the new state-of-the-art.

Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]". Based on exhaustive text cues in "[CONTEXT]", CLIP model is aware of different contexts, e.g. background, style, viewpoint, and exhibits unprecedented robustness against a wide range of distribution shifts. However, recent works find further fine-tuning of CLIP models improves accuracy but sacrifices the robustness on downstream tasks. We conduct an empirical investigation to show fine-tuning will corrupt the context-aware ability of pre-trained CLIP features. To solve this problem, we propose Context-Aware Robust Fine-tuning (CAR-FT). CAR-FT regularizes the model during fine-tuning to capture the context information. Specifically, we use zero-shot prompt weights to get the context distribution contained in the image. By minimizing the Kullback-Leibler Divergence (KLD) between context distributions induced by original/fine-tuned CLIP models, CAR-FT makes the context-aware ability of CLIP inherited into downstream tasks, and achieves both higher In-Distribution (ID) and Out-Of-Distribution (OOD) accuracy. The experimental results show CAR-FT achieves superior robustness on five OOD test datasets of ImageNet, and meanwhile brings accuracy gains on nine downstream tasks. Additionally, CAR-FT surpasses previous Domain Generalization (DG) methods and gets 78.5% averaged accuracy on DomainBed benchmark, building the new state-of-the-art.

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the true positive rate, which often shows poor attack performance, as another sub-optimal bounding box may be detected around the attacked bounding box to be the new true positive one. To settle this challenge, we propose to minimize the true positive rate and maximize the false positive rate, which can encourage more false positive objects to block the generation of new true positive bounding boxes. It is modeled as a multi-objective optimization (MOP) problem, of which the generic algorithm can search the Pareto-optimal. However, our task has more than two million decision variables, leading to low searching efficiency. Thus, we extend the standard Genetic Algorithm with Random Subset selection and Divide-and-Conquer, called GARSDC, which significantly improves the efficiency. Moreover, to alleviate the sensitivity to population quality in generic algorithms, we generate a gradient-prior initial population, utilizing the transferability between different detectors with similar backbones. Compared with the state-of-art attack methods, GARSDC decreases by an average 12.0 in the mAP and queries by about 1000 times in extensive experiments. Our codes can be found at https://github.com/LiangSiyuan21/ GARSDC., Comment: 14 pages, 5 figures, ECCV2022

Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performed DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property for its owner. However, recent studies revealed the threats of model stealing, where the adversaries can obtain a function-similar copy of the victim model, even when they can only query the model. In this paper, we propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously, without introducing new security risks. In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by tempering a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. In particular, we develop our MOVE method under both white-box and black-box settings to provide comprehensive model protection. Extensive experiments on benchmark datasets verify the effectiveness of our method and its resistance to potential adaptive attacks. The codes for reproducing the main experiments of our method are available at \url{https://github.com/THUYimingLi/MOVE}., Comment: 15 pages. The journal extension of our conference paper in AAAI 2022 (https://ojs.aaai.org/index.php/AAAI/article/view/20036). arXiv admin note: substantial text overlap with arXiv:2112.03476

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and dramatically decreases. Though several FAT variants spare no effort to prevent overfitting, they sacrifice much calculation cost. In this paper, we explore the difference between the training processes of SAT and FAT and observe that the attack success rate of adversarial examples (AEs) of FAT gets worse gradually in the late training stage, resulting in overfitting. The AEs are generated by the fast gradient sign method (FGSM) with a zero or random initialization. Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process. The initialization is formed by leveraging historically generated AEs without additional calculation cost. We further provide a theoretical analysis for the proposed initialization method. We also propose a simple yet effective regularizer based on the prior-guided initialization,i.e., the currently generated perturbation should not deviate too much from the prior-guided initialization. The regularizer adopts both historical and current adversarial perturbations to guide the model learning. Evaluations on four datasets demonstrate that the proposed method can prevent catastrophic overfitting and outperform state-of-the-art FAT methods. The code is released at https://github.com/jiaxiaojunQAQ/FGSM-PGI., Comment: ECCV 2022

As a common security tool, visible watermarking has been widely applied to protect copyrights of digital images. However, recent works have shown that visible watermarks can be removed by DNNs without damaging their host images. Such watermark-removal techniques pose a great threat to the ownership of images. Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good. From the perspective of the adversary, blind watermark-removal networks can be posed as our target models; then we actually optimize an imperceptible adversarial perturbation on the host images to proactively attack against watermark-removal networks, dubbed Watermark Vaccine. Specifically, two types of vaccines are proposed. Disrupting Watermark Vaccine (DWV) induces to ruin the host image along with watermark after passing through watermark-removal networks. In contrast, Inerasable Watermark Vaccine (IWV) works in another fashion of trying to keep the watermark not removed and still noticeable. Extensive experiments demonstrate the effectiveness of our DWV/IWV in preventing watermark removal, especially on various watermark removal networks., Comment: ECCV 2022

Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient Decent (PGD) with manually specifying attack parameters for AE generation. A combination of the attack parameters can be referred to as an attack strategy. Several works have revealed that using a fixed attack strategy to generate AEs during the whole training phase limits the model robustness and propose to exploit different attack strategies at different training stages to improve robustness. But those multi-stage hand-crafted attack strategies need much domain expertise, and the robustness improvement is limited. In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness. Our framework is composed of a target network that uses AEs for training to improve robustness and a strategy network that produces attack strategies to control the AE generation. Experimental evaluations on three benchmark databases demonstrate the superiority of the proposed method. The code is released at https://github.com/jiaxiaojunQAQ/LAS-AT.

Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adversaries can `steal' deployed models even when they have no training samples and can not get access to the model parameters or structures. Currently, there were some defense methods to alleviate this threat, mostly by increasing the cost of model stealing. In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified \emph{external features}. Specifically, we embed the external features by tempering a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. We examine our method on both CIFAR-10 and ImageNet datasets. Experimental results demonstrate that our method is effective in detecting different types of model stealing simultaneously, even if the stolen model is obtained via a multi-stage stealing process. The codes for reproducing main results are available at Github (https://github.com/zlh-thu/StealingVerification)., Comment: This work is accepted by the AAAI 2022. The first two authors contributed equally to this work. 11 pages

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating gradients at multiple steps in generating adversarial examples. To boost training efficiency, fast gradient sign method (FGSM) is adopted in fast AT methods by calculating gradient only once. Unfortunately, the robustness is far from satisfactory. One reason may arise from the initialization fashion. Existing fast AT generally uses a random sample-agnostic initialization, which facilitates the efficiency yet hinders a further robustness improvement. Up to now, the initialization in fast AT is still not extensively explored. In this paper, we boost fast AT with a sample-dependent adversarial initialization, i.e., an output from a generative network conditioned on a benign image and its gradient information from the target network. As the generative network and the target network are optimized jointly in the training phase, the former can adaptively generate an effective initialization with respect to the latter, which motivates gradually improved robustness. Experimental evaluations on four benchmark databases demonstrate the superiority of our proposed method over state-of-the-art fast AT methods, as well as comparable robustness to advanced multi-step AT methods. The code is released at https://github.com//jiaxiaojunQAQ//FGSM-SDI., Comment: Accepted by TIP

In recent years, intellectual property (IP), which represents literary, inventions, artistic works, etc, gradually attract more and more people's attention. Particularly, with the rise of e-commerce, the IP not only represents the product design and brands, but also represents the images/videos displayed on e-commerce platforms. Unfortunately, some attackers adopt some adversarial methods to fool the well-trained logo detection model for infringement. To overcome this problem, a novel logo detector based on the mechanism of looking and thinking twice is proposed in this paper for robust logo detection. The proposed detector is different from other mainstream detectors, which can effectively detect small objects, long-tail objects, and is robust to adversarial images. In detail, we extend detectoRS algorithm to a cascade schema with an equalization loss function, multi-scale transformations, and adversarial data augmentation. A series of experimental results have shown that the proposed method can effectively improve the robustness of the detection model. Moreover, we have applied the proposed methods to competition ACM MM2021 Robust Logo Detection that is organized by Alibaba on the Tianchi platform and won top 2 in 36489 teams. Code is available at https://github.com/jiaxiaojunQAQ/Robust-Logo-Detection., Comment: 5 pages

Recent research has demonstrated that adding some imperceptible perturbations to original images can fool deep learning models. However, the current adversarial perturbations are usually shown in the form of noises, and thus have no practical meaning. Image watermark is a technique widely used for copyright protection. We can regard image watermark as a king of meaningful noises and adding it to the original image will not affect people's understanding of the image content, and will not arouse people's suspicion. Therefore, it will be interesting to generate adversarial examples using watermarks. In this paper, we propose a novel watermark perturbation for adversarial examples (Adv-watermark) which combines image watermarking techniques and adversarial example algorithms. Adding a meaningful watermark to the clean images can attack the DNN models. Specifically, we propose a novel optimization algorithm, which is called Basin Hopping Evolution (BHE), to generate adversarial watermarks in the black-box attack mode. Thanks to the BHE, Adv-watermark only requires a few queries from the threat models to finish the attacks. A series of experiments conducted on ImageNet and CASIA-WebFace datasets show that the proposed method can efficiently generate adversarial examples, and outperforms the state-of-the-art attack methods. Moreover, Adv-watermark is more robust against image transformation defense methods.

Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this paper, we propose an effective defense framework to characterize and defend adversarial videos. The proposed method contains two phases: (1) adversarial video detection using temporal consistency between adjacent frames, and (2) adversarial perturbation reduction via denoisers in the spatial and temporal domains respectively. Specifically, because of the linear nature of DNNs, the imperceptible perturbations will enlarge with the increasing of DNNs depth, which leads to the inconsistency of DNNs output between adjacent frames. However, the benign video frames often have the same outputs with their neighbor frames owing to the slight changes. Based on this observation, we can distinguish between adversarial videos and benign videos. After that, we utilize different defense strategies against different attacks. We propose the temporal defense, which reconstructs the polluted frames with their temporally neighbor clean frames, to deal with the adversarial videos with sparse polluted frames. For the videos with dense polluted frames, we use an efficient adversarial denoiser to process each frame in the spatial domain, and thus purify the perturbations (we call it as spatial defense). A series of experiments conducted on the UCF-101 dataset demonstrate that the proposed method significantly improves the robustness of video classifiers against adversarial attacks.

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: \textbf{ComDefend}. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is used to reconstruct the original image with high quality. In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier. Our method is a pre-processing module, and does not modify the classifier's structure during the whole process. Therefore, it can be combined with other model-specific defense models to jointly improve the classifier's robustness. A series of experiments conducted on MNIST, CIFAR10 and ImageNet show that the proposed method outperforms the state-of-the-art defense methods, and is consistently effective to protect classifiers against adversarial attacks.

Purpose: This paper combines a synthetic index system by the variables and evaluates China’s financial safety through the change of indexes in a comprehensive way. First of all, it builds the financial industry evaluation index system composed of 25indicators in terms of the operation of the financial industry and external economic environment and particularly takes into consideration factors which might trigger liquidity risks such as off-balance-sheet business, interbank business and shadow banking; then it selects 10 indicators to conduct empirical analysis and identifies the indicator weight through principal component analysis; finally it combines the financial safety indexes through the linear weighted comprehensive evaluation model. Design/methodology/approach: Synthesis of indexes is made by constructing a proper comprehensive evaluation mathematical model, integrating a number of evaluation indexes into one comprehensive evaluation index and then obtaining corresponding comprehensive evaluation results. In this paper, it selects 10 indexes to conduct empirical analysis and identifies the index weight through principal component analysis; finally it combines the financial safety indexes through the linear weighted comprehensive evaluation model. Principal component analysis (PCA) is a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components. PCA was invented in 1901 and was later independently developed (and named) by Harold Hotelling in the 1930s. Findings: From 2003 to 2013 China’s financial safety indexes fluctuated. From 2003 to 2007 indexes rose, which indicates China’s financial safety status gradually improved; from 2007 to 2009 indexes declined, which indicates due to the impact of subprime crisis, China’s financial safety status took a turn for the worse; from 2009 to 2012 indexes rose, which indic, Peer Reviewed