Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks

25 May 2019

Papers citing "Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks"

5 / 5 papers shown

Title
Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems Jirong Yi Q. Zhang Zhengbo Chen Qiaoan Liu Weizhuo Shao Yusen He Yao Wang SSL 28 0 0 23 Nov 2022
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems Jirong Yi Q. Zhang Zhenji Chen Qiaoan Liu Weizhuo Shao SSL FedML 34 3 0 21 Sep 2022
An Adaptive Black-box Defense against Trojan Attacks (TrojDef) Guanxiong Liu Abdallah Khreishah Fatima Sharadgah Issa M. Khalil AAML 30 8 0 05 Sep 2022
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning Jirong Yi R. Mudumbai Weiyu Xu AAML 32 2 0 28 Jul 2020
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 317 5,847 0 08 Jul 2016