Search

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 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.

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

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.

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.

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

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

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.