paper-with-me

홈 › Papers

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement

2024-03-14 · CVPR 2024 1 · Daiwei Yu, Zhuorong Li, Lina Wei, Canghong Jin, Yun Zhang, Sixian Chan

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization gap in adversarial robustness between the training and testing curves. In this paper, we first identify a connection between robust overfitting and the excessive memorization of noisy labels in AT from a view of gradient norm. As such label noise is mainly caused by a distribution mismatch and improper label assignments, we are motivated to propose a label refinement approach for AT. Specifically, our Self-Guided Label Refinement first self-refines a more accurate and informative label distribution from over-confident hard labels, and then it calibrates the training by dynamically incorporating knowledge from self-distilled models into the current model and thus requiring no external teachers. Empirical results demonstrate that our method can simultaneously boost the standard accuracy and robust performance across multiple benchmark datasets, attack types, and architectures. In addition, we also provide a set of analyses from the perspectives of information theory to dive into our method and suggest the importance of soft labels for robust generalization.

📄 PDF Abstract BibTeX arXiv:2403.09101

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessMemorization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Deflecting Adversarial Attacks with Pixel Deflection

2018-01-26 · CVPR 2018 6 · Aaditya Prakash, Nick Moran, Solomon Garber, Antonella DiLillo 외

CNNs are poised to become integral parts of many critical systems. Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to caus…

Adversarial Attack

Improving Fast Adversarial Training via Self-Knowledge Guidance

2024-09-26 · Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui 외

Adversarial training has achieved remarkable advancements in defending against adversarial attacks. Among them, fast adversarial training (FAT) is gaining attention for its ability to achieve competitive robustness with …

Adversarial RobustnessAttribute

Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models

2026-01-24 · Yicheng Bao, Xuhong Wang, Qiaosheng Zhang, Chaochao Lu 외 arxiv

Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, …

Reinforcement Learning

The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play

2026-05-08 · Gabriele La Malfa, Emanuele La Malfa, Saar Cohen, Jie M. Zhang 외 arxiv

Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where the attacker tries to jailbreak the def…

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

2026-02-01 · Songping Wang, Qinglong Liu, Yueming Lyu, Ning Li 외 arxiv

Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often treat MoE as a unified architecture, overlook…

Adversarial Robustness