20 citations · 57 across the 18 of their papers we have counts for
4 papers · 1 filter
Feature compression is the root cause of adversarial fragility in neural network classifiers
Jingchao Gao, Ziqing Lu, Raghu Mudumbai +6
In this paper, we uniquely study the adversarial robustness of deep neural networks (NN) for classification tasks against that of optimal classifiers. We look at the smallest magni…
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Jirong Yi, Qiaosheng Zhang, Zhen Chen +2
Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained clas…
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Jirong Yi, Qiaosheng Zhang, Zhen Chen +2
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets…
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning
Jirong Yi, Raghu Mudumbai, Weiyu Xu
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by…