11 citations · 22 across the 6 of their papers we have counts for
6 papers
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…
gcDLSeg: Integrating Graph-cut into Deep Learning for Binary Semantic Segmentation
Hui Xie, Weiyu Xu, Ya Xing Wang +2
Binary semantic segmentation in computer vision is a fundamental problem. As a model-based segmentation method, the graph-cut approach was one of the most successful binary segment…
Globally Optimal Segmentation of Mutually Interacting Surfaces using Deep Learning
Hui Xie, Zhe Pan, Leixin Zhou +5
Segmentation of multiple surfaces in medical images is a challenging problem, further complicated by the frequent presence of weak boundary and mutual influence between adjacent ob…
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
Jirong Yi, Hui Xie, Leixin Zhou +3
Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outp…
An Information-Theoretic Explanation for the Adversarial Fragility of AI Classifiers
Hui Xie, Jirong Yi, Weiyu Xu +1
We present a simple hypothesis about a compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully…
Finite automata for testing uniqueness of Eulerian trails
Qiang Li, Hui-Min Xie
We investigate the condition under which the Eulerian trail of a digraph is unique, and design a finite automaton to examine it. The algorithm is effective, for if the condition is…