On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from a fundamental tradeoff that inevitably decreases clean accuracy. Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization. However, as SAM is designed for better clean accuracy, its effectiveness in enhancing adversarial robustness remains unexplored. In this work, considering the duality between SAM and AT, we investigate the adversarial robustness derived from SAM. Intriguingly, we find that using SAM alone can improve adversarial robustness. To understand this unexpected property of SAM, we first provide empirical and theoretical insights into how SAM can implicitly learn more robust features, and conduct comprehensive experiments to show that SAM can improve adversarial robustness notably without sacrificing any clean accuracy, shedding light on the potential of SAM to be a substitute for AT when accuracy comes at a higher priority. Code is available at https://github.com/weizeming/SAM_AT.

Your Diffusion Model is Secretly a Certifiably Robust Classifier

Diffusion models are recently employed as generative classifiers for robust classification. However, a comprehensive theoretical understanding of the robustness of diffusion classifiers is still lacking, leading us to question whether they will be vulnerable to future stronger attacks. In this study, we propose a new family of diffusion classifiers, named Noised Diffusion Classifiers~(NDCs), that possess state-of-the-art certified robustness. Specifically, we generalize the diffusion classifiers to classify Gaussian-corrupted data by deriving the evidence lower bounds (ELBOs) for these distributions, approximating the likelihood using the ELBO, and calculating classification probabilities via Bayes' theorem. We integrate these generalized diffusion classifiers with randomized smoothing to construct smoothed classifiers possessing non-constant Lipschitzness. Experimental results demonstrate the superior certified robustness of our proposed NDCs. Notably, we are the first to achieve 80\%+ and 70\%+ certified robustness on CIFAR-10 under adversarial perturbations with $\ell_2$ norm less than 0.25 and 0.5, respectively, using a single off-the-shelf diffusion model without any additional data.

Precise Knowledge Transfer via Flow Matching

In this paper, we propose a novel knowledge transfer framework that introduces continuous normalizing flows for progressive knowledge transformation and leverages multi-step sampling strategies to achieve precision knowledge transfer. We name this framework Knowledge Transfer with Flow Matching (FM-KT), which can be integrated with a metric-based distillation method with any form (\textit{e.g.} vanilla KD, DKD, PKD and DIST) and a meta-encoder with any available architecture (\textit{e.g.} CNN, MLP and Transformer). By introducing stochastic interpolants, FM-KD is readily amenable to arbitrary noise schedules (\textit{e.g.}, VP-ODE, VE-ODE, Rectified flow) for normalized flow path estimation. We theoretically demonstrate that the training objective of FM-KT is equivalent to minimizing the upper bound of the teacher feature map or logit negative log-likelihood. Besides, FM-KT can be viewed as a unique implicit ensemble method that leads to performance gains. By slightly modifying the FM-KT framework, FM-KT can also be transformed into an online distillation framework OFM-KT with desirable performance gains. Through extensive experiments on CIFAR-100, ImageNet-1k, and MS-COCO datasets, we empirically validate the scalability and state-of-the-art performance of our proposed methods among relevant comparison approaches.

Rethinking Centered Kernel Alignment in Knowledge Distillation

Knowledge distillation has emerged as a highly effective method for bridging the representation discrepancy between large-scale models and lightweight models. Prevalent approaches involve leveraging appropriate metrics to minimize the divergence or distance between the knowledge extracted from the teacher model and the knowledge learned by the student model. Centered Kernel Alignment (CKA) is widely used to measure representation similarity and has been applied in several knowledge distillation methods. However, these methods are complex and fail to uncover the essence of CKA, thus not answering the question of how to use CKA to achieve simple and effective distillation properly. This paper first provides a theoretical perspective to illustrate the effectiveness of CKA, which decouples CKA to the upper bound of Maximum Mean Discrepancy~(MMD) and a constant term. Drawing from this, we propose a novel Relation-Centered Kernel Alignment~(RCKA) framework, which practically establishes a connection between CKA and MMD. Furthermore, we dynamically customize the application of CKA based on the characteristics of each task, with less computational source yet comparable performance than the previous methods. The extensive experiments on the CIFAR-100, ImageNet-1k, and MS-COCO demonstrate that our method achieves state-of-the-art performance on almost all teacher-student pairs for image classification and object detection, validating the effectiveness of our approaches.

How Robust is Google's Bard to Adversarial Image Attacks?

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision models, MLLMs can have more severe safety and security risks by introducing the vision inputs. In this work, we study the adversarial robustness of Google's Bard, a competitive chatbot to ChatGPT that released its multimodal capability recently, to better understand the vulnerabilities of commercial MLLMs. By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability. We show that the adversarial examples can also attack other MLLMs, e.g., a 26% attack success rate against Bing Chat and a 86% attack success rate against ERNIE bot. Moreover, we identify two defense mechanisms of Bard, including face detection and toxicity detection of images. We design corresponding attacks to evade these defenses, demonstrating that the current defenses of Bard are also vulnerable. We hope this work can deepen our understanding on the robustness of MLLMs and facilitate future research on defenses. Our code is available at https://github.com/thu-ml/Attack-Bard.

Enhancing Adversarial Attacks: The Similar Target Method

Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. An intriguing property of adversarial examples is their strong transferability. Several methods have been proposed to enhance transferability, including ensemble attacks which have demonstrated their efficacy. However, prior approaches simply average logits, probabilities, or losses for model ensembling, lacking a comprehensive analysis of how and why model ensembling significantly improves transferability. In this paper, we propose a similar targeted attack method named Similar Target~(ST). By promoting cosine similarity between the gradients of each model, our method regularizes the optimization direction to simultaneously attack all surrogate models. This strategy has been proven to enhance generalization ability. Experimental results on ImageNet validate the effectiveness of our approach in improving adversarial transferability. Our method outperforms state-of-the-art attackers on 18 discriminative classifiers and adversarially trained models.

Boosting Adversarial Attack with Similar Target

Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. An intriguing property of adversarial examples is their strong transferability. Several methods have been proposed to enhance transferability, including ensemble attacks which have demonstrated their efficacy. However, prior approaches simply average logits, probabilities, or losses for model ensembling, lacking a comprehensive analysis of how and why model ensembling significantly improves transferability. In this paper, we propose a similar targeted attack method named Similar Target~(ST). By promoting cosine similarity between the gradients of each model, our method regularizes the optimization direction to simultaneously attack all surrogate models. This strategy has been proven to enhance generalization ability. Experimental results on ImageNet validate the effectiveness of our approach in improving adversarial transferability. Our method outperforms state-of-the-art attackers on 18 discriminative classifiers and adversarially trained models.

AFN: Adaptive Fusion Normalization via Encoder-Decoder Framework

The success of deep learning is inseparable from normalization layers. Researchers have proposed various normalization functions, and each of them has both advantages and disadvantages. In response, efforts have been made to design a unified normalization function that combines all normalization procedures and mitigates their weaknesses. We also proposed a new normalization function called Adaptive Fusion Normalization. Through experiments, we demonstrate AFN outperforms the previous normalization techniques in domain generalization and image classification tasks.

Robust Classification via a Single Diffusion Model

Recently, diffusion models have been successfully applied to improving adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, the diffusion-based purification can be evaded by stronger adaptive attacks while adversarial training does not perform well under unseen threats, exhibiting inevitable limitations of these methods. To better harness the expressive power of diffusion models, in this paper we propose Robust Diffusion Classifier (RDC), a generative classifier that is constructed from a pre-trained diffusion model to be adversarially robust. Our method first maximizes the data likelihood of a given input and then predicts the class probabilities of the optimized input using the conditional likelihood of the diffusion model through Bayes' theorem. Since our method does not require training on particular adversarial attacks, we demonstrate that it is more generalizable to defend against multiple unseen threats. In particular, RDC achieves $73.24\%$ robust accuracy against $\ell_\infty$ norm-bounded perturbations with $\epsilon_\infty=8/255$ on CIFAR-10, surpassing the previous state-of-the-art adversarial training models by $+2.34\%$. The findings highlight the potential of generative classifiers by employing diffusion models for adversarial robustness compared with the commonly studied discriminative classifiers.