Adversarial scratches: Deployable attacks to CNN classifiers

Pattern Recognition(2023)

引用 6|浏览51
暂无评分
摘要
•We present Adversarial Scratches, a powerful attack to CNN classifiers.•Adversarial Scratches are designed to be deployable over a target image region.•We adopt Bezier Curves to reduce the dimensionality of the search space.•Adversarial Scratches yield state-of-the-art performance amongst deployable attacks.•We propose image filtering defenses and investigate their impact on healthy images.
更多
查看译文
关键词
Adversarial perturbations,Adversarial attacks,Deep learning,Convolutional neural networks,Bézier curves
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