paper-with-me

Papers

Maintaining Adversarial Robustness in Continuous Learning

2024-02-17 · Xiaolei Ru, Xiaowei Cao, Zijia Liu, Jack Murdoch Moore, Xin-Ya Zhang, Xia Zhu, Wenjia Wei, Gang Yan

Adversarial robustness is essential for security and reliability of machine learning systems. However, adversarial robustness enhanced by defense algorithms is easily erased as the neural network's weights update to learn new tasks. To address this vulnerability, it is essential to improve the capability of neural networks in terms of robust continual learning. Specially, we propose a novel gradient projection technique that effectively stabilizes sample gradients from previous data by orthogonally projecting back-propagation gradients onto a crucial subspace before using them for weight updates. This technique can maintaining robustness by collaborating with a class of defense algorithms through sample gradient smoothing. The experimental results on four benchmarks including Split-CIFAR100 and Split-miniImageNet, demonstrate that the superiority of the proposed approach in mitigating rapidly degradation of robustness during continual learning even when facing strong adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2402.11196

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessContinual Learning

Similar Papers 제목 키워드 기반

Efficient Adversarial Training in LLMs with Continuous Attacks

2024-05-24 · Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel 외

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most promising methods to reliably improve rob…

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

2025-05-22 · Csaba Dékány, Stefan Balauca, Robin Staab, Dimitar I. Dimitrov 외

Despite recent efforts in Large Language Models (LLMs) safety and alignment, current adversarial attacks on frontier LLMs are still able to force harmful generations consistently. Although adversarial training has been w…

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

2024-04-09 · Jianlang Chen, Xuhong Ren, Qing Guo, Felix Juefei-Xu 외

Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field…

ObjectObject TrackingVisual Object Tracking

Information Theoretic Adversarial Training of Large Language Models

2026-05-06 · Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi, Rouzbeh Behnia 외 arxiv

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve r…

Universal Adversarial Robustness of Texture and Shape-Biased Models

2019-11-23 · Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan, Ben Glocker 외

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adve…

Adversarial RobustnessImage Classification