首页|Researchers Submit Patent Application, 'Device And Method For Determining Adversarial Perturbations Of A Machine Learning System', for Approval (USPTO 20230418246)
Researchers Submit Patent Application, 'Device And Method For Determining Adversarial Perturbations Of A Machine Learning System', for Approval (USPTO 20230418246)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
News editors obtained the following quote from the background information supplied by the inventors:“Ballet et al. “Imperceptible Adversarial Attacks on Tabular Data”, 2019, https://arxiv.org/pdf/1911.03274.pdf describes the notion of adversarial examples in the tabular domain. The authors proposea formalization based on the imperceptibility of attacks in the tabular domain leading to an approach togenerate imperceptible adversarial examples. Experiments show that imperceptible adversarial examplescan be generated with a high fooling rate.
NETL
NSTL
