Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
arxiv(2024)
摘要
Adversarial Training (AT) effectively improves the robustness of Deep Neural
Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN
models with adversarial examples obtained within a pre-defined, fixed
perturbation bound. Notably, individual natural examples from which these
adversarial examples are crafted exhibit varying degrees of intrinsic
vulnerabilities, and as such, crafting adversarial examples with fixed
perturbation radius for all instances may not sufficiently unleash the potency
of AT. Motivated by this observation, we propose two simple, computationally
cheap vulnerability-aware reweighting functions for assigning perturbation
bounds to adversarial examples used for AT, named Margin-Weighted Perturbation
Budget (MWPB) and Standard-Deviation-Weighted Perturbation Budget (SDWPB). The
proposed methods assign perturbation radii to individual adversarial samples
based on the vulnerability of their corresponding natural examples.
Experimental results show that the proposed methods yield genuine improvements
in the robustness of AT algorithms against various adversarial attacks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要