Search

Teeth localization, segmentation, and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, general instance segmentation frameworks are incompetent due to 1) the subtle differences between some teeth' shapes (e.g., maxillary first premolar and second premolar), 2) the teeth's position and shape variation across subjects, and 3) the presence of abnormalities in the dentition (e.g., caries and edentulism). To address these problems, we propose a ViT-based framework named TeethSEG, which consists of stacked Multi-Scale Aggregation (MSA) blocks and an Anthropic Prior Knowledge (APK) layer. Specifically, to compose the two modules, we design 1) a unique permutation-based upscaler to ensure high efficiency while establishing clear segmentation boundaries with 2) multi-head self/cross-gating layers to emphasize particular semantics meanwhile maintaining the divergence between token embeddings. Besides, we collect 3) the first open-sourced intraoral image dataset IO150K, which comprises over 150k intraoral photos, and all photos are annotated by orthodontists using a human-machine hybrid algorithm. Experiments on IO150K demonstrate that our TeethSEG outperforms the state-of-the-art segmentation models on dental image segmentation., Comment: This paper has been accepted by CVPR 2024

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image, resulting in excessive noise that overfit the source model. Concentrating perturbation to dominant image regions that are model-agnostic is crucial to improving adversarial efficacy. However, limiting perturbation to local regions in the spatial domain proves inadequate in augmenting transferability. To this end, we propose a transferable adversarial attack with fine-grained perturbation optimization in the frequency domain, creating centralized perturbation. We devise a systematic pipeline to dynamically constrain perturbation optimization to dominant frequency coefficients. The constraint is optimized in parallel at each iteration, ensuring the directional alignment of perturbation optimization with model prediction. Our approach allows us to centralize perturbation towards sample-specific important frequency features, which are shared by DNNs, effectively mitigating source model overfitting. Experiments demonstrate that by dynamically centralizing perturbation on dominating frequency coefficients, crafted adversarial examples exhibit stronger transferability, and allowing them to bypass various defenses., Comment: 10 pages, 9 figures, accepted by AAAI 2024

Deep learning techniques have implemented many unconditional image generation (UIG) models, such as GAN, Diffusion model, etc. The extremely realistic images (also known as AI-Generated Content, AIGC for short) produced by these models bring urgent needs for intellectual property protection such as data traceability and copyright certification. An attacker can steal the output images of the target model and use them as part of the training data to train a private surrogate UIG model. The implementation mechanisms of UIG models are diverse and complex, and there is no unified and effective protection and verification method at present. To address these issues, we propose a two-stage unified watermark verification mechanism with high-binding effects for such models. In the first stage, we use an encoder to invisibly write the watermark image into the output images of the original AIGC tool, and reversely extract the watermark image through the corresponding decoder. In the second stage, we design the decoder fine-tuning process, and the fine-tuned decoder can make correct judgments on whether the suspicious model steals the original AIGC tool data. Experiments demonstrate our method can complete the verification work with almost zero false positive rate under the condition of only using the model output images. Moreover, the proposed method can achieve data steal verification across different types of UIG models, which further increases the practicality of the method.

Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden indefinitely until activated by a sample with a specific trigger, which is hugely concealed. Nevertheless, existing backdoor attacks operate backdoors in spatial domain, i.e., the poisoned images are generated by adding additional perturbations to the original images, which are easy to detect. To bring the potential of backdoor attacks into full play, we propose low-pass attack, a novel attack scheme that utilizes low-pass filter to inject backdoor in frequency domain. Unlike traditional poisoned image generation methods, our approach reduces high-frequency components and preserve original images' semantic information instead of adding additional perturbations, improving the capability of evading current defenses. Besides, we introduce "precision mode" to make our backdoor triggered at a specified level of filtering, which further improves stealthiness. We evaluate our low-pass attack on four datasets and demonstrate that even under pollution rate of 0.01, we can perform stealthy attack without trading off attack performance. Besides, our backdoor attack can successfully bypass state-of-the-art defending mechanisms. We also compare our attack with existing backdoor attacks and show that our poisoned images are nearly invisible and retain higher image quality.

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By injecting malicious data into the training set, an adversary can plant the backdoor into the original model. The backdoor can remain hidden indefinitely until activated by a sample with a specific trigger, which is hugely concealed, bringing serious security risks to critical applications. However, one main limitation of current backdoor attacks is that the trigger is often visible to human perception. Therefore, it is crucial to study the stealthiness of backdoor triggers. In this paper, we propose a novel frequency-domain backdooring technique. In particular, our method aims to add a backdoor trigger in the frequency domain of original images via Discrete Fourier Transform, thus hidding the trigger. We evaluate our method on three benchmark datasets: MNIST, CIFAR-10 and Imagenette. Our experiments show that we can simultaneously fool human inspection and DNN models. We further apply two image similarity evaluation metrics to illustrate that our method adds the most subtle perturbation without compromising attack success rate and clean sample accuracy., Comment: arXiv admin note: text overlap with arXiv:2305.09677

Digital twin has recently attracted growing attention, leading to intensive research and applications. Along with this, a new research area, dubbed as "human digital twin" (HDT), has emerged. Similar to the conception of digital twin, HDT is referred to as the replica of a physical-world human in the digital world. Nevertheless, HDT is much more complicated and delicate compared to digital twins of any physical systems and processes, due to humans' dynamic and evolutionary nature, including physical, behavioral, social, physiological, psychological, cognitive, and biological dimensions. Studies on HDT are limited, and the research is still in its infancy. In this paper, we first examine the inception, development, and application of the digital twin concept, providing a context within which we formally define and characterize HDT based on the similarities and differences between digital twin and HDT. Then we conduct an extensive literature review on HDT research, analyzing underpinning technologies and establishing typical frameworks in which the core HDT functions or components are organized. Built upon the findings from the above work, we propose a generic architecture for the HDT system and describe the core function blocks and corresponding technologies. Following this, we present the state of the art of HDT technologies and applications in the healthcare, industry, and daily life domain. Finally, we discuss various issues related to the development of HDT and point out the trends and challenges of future HDT research and development.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track., Comment: Technical report of AISC

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible. To solve these problems, we propose a two-phase and image-specific triggers generation method to enhance clean-label backdoor attacks. Our methods are (1) powerful: our triggers can both promote the two phases (i.e., the backdoor implantation and activation phase) in backdoor attacks simultaneously; (2) stealthy: our triggers are generated from each image. They are image-specific instead of fixed triggers. Extensive experiments demonstrate that our approach can achieve a fantastic attack success rate~(98.98%) with low poisoning rate~(5%), high stealthiness under many evaluation metrics and is resistant to backdoor defense methods.

Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, especially Membership Inference Attacks (MIAs), the objective of which is to infer the model's training data. So far, most of the membership inference attacks against ML classifiers leverage the shadow model with the same structure as the target model. However, empirical results show that these attacks can be easily mitigated if the shadow model is not clear about the network structure of the target model. In this paper, We present attacks based on black-box access to the target model. We name our attack \textbf{l-Leaks}. The l-Leaks follows the intuition that if an established shadow model is similar enough to the target model, then the adversary can leverage the shadow model's information to predict a target sample's membership.The logits of the trained target model contain valuable sample knowledge. We build the shadow model by learning the logits of the target model and making the shadow model more similar to the target model. Then shadow model will have sufficient confidence in the member samples of the target model. We also discuss the effect of the shadow model's different network structures to attack results. Experiments over different networks and datasets demonstrate that both of our attacks achieve strong performance., Comment: 10pages,6figures

Vision transformers (ViTs) have demonstrated impressive performance in various computer vision tasks. However, the adversarial examples generated by ViTs are challenging to transfer to other networks with different structures. Recent attack methods do not consider the specificity of ViTs architecture and self-attention mechanism, which leads to poor transferability of the generated adversarial samples by ViTs. We attack the unique self-attention mechanism in ViTs by restructuring the embedded patches of the input. The restructured embedded patches enable the self-attention mechanism to obtain more diverse patches connections and help ViTs keep regions of interest on the object. Therefore, we propose an attack method against the unique self-attention mechanism in ViTs, called Self-Attention Patches Restructure (SAPR). Our method is simple to implement yet efficient and applicable to any self-attention based network and gradient transferability-based attack methods. We evaluate attack transferability on black-box models with different structures. The result show that our method generates adversarial examples on white-box ViTs with higher transferability and higher image quality. Our research advances the development of black-box transfer attacks on ViTs and demonstrates the feasibility of using white-box ViTs to attack other black-box models.

The security of models based on new architectures such as MLP-Mixer and ViTs needs to be studied urgently. However, most of the current researches are mainly aimed at the adversarial attack against ViTs, and there is still relatively little adversarial work on MLP-mixer. We propose an adversarial attack method against MLP-Mixer called Maxwell's demon Attack (MA). MA breaks the channel-mixing and token-mixing mechanism of MLP-Mixer by controlling the part input of MLP-Mixer's each Mixer layer, and disturbs MLP-Mixer to obtain the main information of images. Our method can mask the part input of the Mixer layer, avoid overfitting of the adversarial examples to the source model, and improve the transferability of cross-architecture. Extensive experimental evaluation demonstrates the effectiveness and superior performance of the proposed MA. Our method can be easily combined with existing methods and can improve the transferability by up to 38.0% on MLP-based ResMLP. Adversarial examples produced by our method on MLP-Mixer are able to exceed the transferability of adversarial examples produced using DenseNet against CNNs. To the best of our knowledge, we are the first work to study adversarial transferability of MLP-Mixer.

Measurement-induced nonlocality (MIN) was proposed for measure the maximum global effect caused by locally invariant measurements. Similarly, the Measurement-induced nonbilocal correlation is a generalization of MIN can be used to measure the maximal global influence caused by the local measurement in the bilocal scenario. In this paper, we propose a new nonbilocal correlation measure based on the Wigner-Yanase skew information. The relationship between the MIN based on Wigner-Yanase skew information and our measure is discussed. We present an analytical expression of our measure for pure input states and also provide upper bounds for input general mixed states., Comment: 9 pages

In this paper, we present a classification of $2$-designs with $\gcd(r,\lambda)=1$ admitting flag-transitive automorphism groups. If $G$ is a flag-transitive automorphism group of a non-trivial $2$-design $\mathcal{D}$ with $\gcd(r,\lambda)=1$, then either $(\mathcal{D},G)$ is one of the known examples described in this paper, or $\mathcal{D}$ has $q = p^{d}$ points with $p$ prime and $G$ is a subgroup of $A\Gamma L_{1}(q)$.

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this restriction. In fact, more threats to the deep model come from unrestricted adversarial examples, that is, the attacker makes large and visible modifications on the image, which causes the model classifying mistakenly, but does not affect the normal observation in human perspective. Unrestricted adversarial attack is a popular and practical direction but has not been studied thoroughly. We organize this competition with the purpose of exploring more effective unrestricted adversarial attack algorithm, so as to accelerate the academical research on the model robustness under stronger unbounded attacks. The competition is held on the TianChi platform (\url{https://tianchi.aliyun.com/competition/entrance/531853/introduction}) as one of the series of AI Security Challengers Program., Comment: CVPR-2021 AIC Phase VI Track2: Unrestricted Adversarial Attacks on ImageNet

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight $\Lp$ norm bounds are small, they are still easily perceivable by humans. These perturbations also have limited success rates when attacking black-box models or models with defenses like noise reduction filters. To solve these problems, we propose Demiguise Attack, crafting ``unrestricted'' perturbations with Perceptual Similarity. Specifically, we can create powerful and photorealistic adversarial examples by manipulating semantic information based on Perceptual Similarity. Adversarial examples we generate are friendly to the human visual system (HVS), although the perturbations are of large magnitudes. We extend widely-used attacks with our approach, enhancing adversarial effectiveness impressively while contributing to imperceptibility. Extensive experiments show that the proposed method not only outperforms various state-of-the-art attacks in terms of fooling rate, transferability, and robustness against defenses but can also improve attacks effectively. In addition, we also notice that our implementation can simulate illumination and contrast changes that occur in real-world scenarios, which will contribute to exposing the blind spots of DNNs.