paper-with-me

홈 › Papers

Learning to Transform Dynamically for Better Adversarial Transferability

2024-05-23 · CVPR 2024 1 · Rongyi Zhu, Zeliang Zhang, Susan Liang, Zhuo Liu, Chenliang Xu

Adversarial examples, crafted by adding perturbations imperceptible to humans, can deceive neural networks. Recent studies identify the adversarial transferability across various models, \textit{i.e.}, the cross-model attack ability of adversarial samples. To enhance such adversarial transferability, existing input transformation-based methods diversify input data with transformation augmentation. However, their effectiveness is limited by the finite number of available transformations. In our study, we introduce a novel approach named Learning to Transform (L2T). L2T increases the diversity of transformed images by selecting the optimal combination of operations from a pool of candidates, consequently improving adversarial transferability. We conceptualize the selection of optimal transformation combinations as a trajectory optimization problem and employ a reinforcement learning strategy to effectively solve the problem. Comprehensive experiments on the ImageNet dataset, as well as practical tests with Google Vision and GPT-4V, reveal that L2T surpasses current methodologies in enhancing adversarial transferability, thereby confirming its effectiveness and practical significance. The code is available at https://github.com/RongyiZhu/L2T.

📄 PDF Abstract BibTeX arXiv:2405.14077

Code (1)

rongyizhu/l2t 공식 구현 pytorch

Tasks

Diversity

Similar Papers 제목 키워드 기반

Structure Invariant Transformation for better Adversarial Transferability

2023-09-26 · ICCV 2023 1 · Xiaosen Wang, Zeliang Zhang, Jianping Zhang

Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial examples, there is an urgent need for an effective adversarial attack to identify the deficiencies of DNNs in security-sensitive applicati…

Adversarial AttackDiversity

Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy

2021-08-16 · Ruikui Wang, Yuanfang Guo, Ruijie Yang, Yunhong Wang

The transferability and robustness of adversarial examples are two practical yet important properties for black-box adversarial attacks. In this paper, we explore effective mechanisms to boost both of them from the persp…

Diversity

Bag of Tricks to Boost Adversarial Transferability

2024-01-16 · Zeliang Zhang, Wei Yao, Xiaosen Wang

Deep neural networks are widely known to be vulnerable to adversarial examples. However, vanilla adversarial examples generated under the white-box setting often exhibit low transferability across different models. Since…

Diversifying the High-level Features for better Adversarial Transferability

2023-04-20 · Zhiyuan Wang, Zeliang Zhang, Siyuan Liang, Xiaosen Wang

Given the great threat of adversarial attacks against Deep Neural Networks (DNNs), numerous works have been proposed to boost transferability to attack real-world applications. However, existing attacks often utilize adv…

Vocal Bursts Intensity Prediction

Admix: Enhancing the Transferability of Adversarial Attacks

2021-01-31 · ICCV 2021 10 · Xiaosen Wang, Xuanran He, Jingdong Wang, Kun He

Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferabili…