可转让性
对抗制
Boosting(机器学习)
透视图(图形)
计算机科学
人工智能
机器学习
罗伊特
作者
Xin Wang,Jie Ren,Shuyun Lin,Xiangming Zhu,Yisen Wang,Quanshi Zhang
出处
期刊:Cornell University - arXiv
日期:2020-01-01
被引量:36
标识
DOI:10.48550/arxiv.2010.04055
摘要
In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations. The negative correlation is further verified through different DNNs with various inputs. Moreover, this negative correlation can be regarded as a unified perspective to understand current transferability-boosting methods. To this end, we prove that some classic methods of enhancing the transferability essentially decease interactions inside adversarial perturbations. Based on this, we propose to directly penalize interactions during the attacking process, which significantly improves the adversarial transferability.
科研通智能强力驱动
Strongly Powered by AbleSci AI