Class-Balanced Universal Perturbations for Adversarial Training
Kexue Ma, Guitao Cao, Mengqian Xu, Chunwei Wu, Hong Wang, Wenming Cao
Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shenzhen University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Universal attack generates image-agnostic perturbation called universal adversarial perturbation (UAP), which can be added to all samples in the data distribution to fool the classifier. However, a universal perturbation will likely mislead the classifier to identify most adversarial examples as the same label, resulting in the imbalance of attack strength between classes. In this paper, we propose class-balanced UAPs that enlarge the dispersion of the predicted labels for adversarial examples. To ensure attack strength and balance simultaneously, we design a novel diversity objective containing probability calibration and penalty regularizer, which fully considers the predicted label distribution between samples and the predicted probability distribution within samples. Furthermore, we apply class-balanced attacks in adversarial training to defend against universal perturbations since the class-balanced UAP provides diverse perturbation directions. We correspondingly reformulate adversarial training from the min-max optimization problem into a new two-stage framework. Experiments on several benchmark datasets demonstrate that the class-balanced attack achieves better performance than the universal attack, while adversarial training with class-balanced UAP achieves state-of-the-art results in clean accuracy and robustness to universal perturbations.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAdversarial Robustness in Machine Learning
Digital Media Forensic Detection · Security and Verification in Computing
参考文献 36
此处列出前 3 条
引用本文 1
按被引量排序,此处列出前 3 条