ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patches
作者：
Highlights：
• We provide a dataset to benchmark machine-learning models against adversarial patches.
• This dataset enables approximating models’ robustness, avoiding a computationally and time-demanding evaluation.
• We tested the effectiveness of the generated adversarial patches against 127 models.
• We showed that the generated adversarial patches are effective when printed and applied to real-world objects.
• We open-source the code to evaluate models robustness using our dataset.
摘要
•We provide a dataset to benchmark machine-learning models against adversarial patches.•This dataset enables approximating models’ robustness, avoiding a computationally and time-demanding evaluation.•We tested the effectiveness of the generated adversarial patches against 127 models.•We showed that the generated adversarial patches are effective when printed and applied to real-world objects.•We open-source the code to evaluate models robustness using our dataset.
论文关键词：Adversarial machine learning,Adversarial patches,Neural networks,Defense,Detection
论文评审过程：Received 1 March 2022, Revised 7 July 2022, Accepted 20 September 2022, Available online 23 September 2022, Version of Record 8 October 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.109064
