Adversarial scratches: Deployable attacks to CNN classifiers
Pattern Recognition(2023)
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
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要