20 citations · 57 across the 18 of their papers we have counts for
18 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…
Outlier Detection Using Generative Models with Theoretical Performance Guarantees
Jirong Yi, Jingchao Gao, Tianming Wang +2
This paper considers the problem of recovering signals modeled by generative models from linear measurements contaminated with sparse outliers. We propose an outlier detection appr…
Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems
Jirong Yi, Qiaosheng Zhang, Zhen Chen +4
As one of the central tasks in machine learning, regression finds lots of applications in different fields. An existing common practice for solving regression problems is the mean…
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…
Optimal Needle Placement for Prostate Rotating-Shield Brachytherapy (RSBT)
Jirong Yi, Quentin E. Adams, Karolyn M. Hopfensperger +5
Purpose: To present an efficient NEEdle Position Optimization (NEEPO) algorithm for prostate rotating shield brachytherapy (RSBT). With RSBT, the increased flexibility beyond conve…
Solving Large Scale Quadratic Constrained Basis Pursuit
Jirong Yi
Inspired by alternating direction method of multipliers and the idea of operator splitting, we propose a efficient algorithm for solving large-scale quadratically constrained basis…
Optimal Pooling Matrix Design for Group Testing with Dilution (Row Degree) Constraints
Jirong Yi, Myung Cho, Xiaodong Wu +2
In this paper, we consider the problem of designing optimal pooling matrix for group testing (for example, for COVID-19 virus testing) with the constraint that no more than s…
Error Correction Codes for COVID-19 Virus and Antibody Testing: Using Pooled Testing to Increase Test Reliability
Jirong Yi, Myung Cho, Xiaodong Wu +2
We consider a novel method to increase the reliability of COVID-19 virus or antibody tests by using specially designed pooled testings. Instead of testing nasal swab or blood sampl…
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…
Low-Cost and High-Throughput Testing of COVID-19 Viruses and Antibodies via Compressed Sensing: System Concepts and Computational Experiments
Jirong Yi, Raghu Mudumbai, Weiyu Xu
Coronavirus disease 2019 (COVID-19) is an ongoing pandemic infectious disease outbreak that has significantly harmed and threatened the health and lives of millions or even billion…
Do Deep Minds Think Alike? Selective Adversarial Attacks for Fine-Grained Manipulation of Multiple Deep Neural Networks
Zain Khan, Jirong Yi, Raghu Mudumbai +2
Recent works have demonstrated the existence of {\it adversarial examples} targeting a single machine learning system. In this paper we ask a simple but fundamental question of "se…
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…
Outlier Detection using Generative Models with Theoretical Performance Guarantees
Jirong Yi, Anh Duc Le, Tianming Wang +2
This paper considers the problem of recovering signals from compressed measurements contaminated with sparse outliers, which has arisen in many applications. In this paper, we prop…
Necessary and Sufficient Null Space Condition for Nuclear Norm Minimization in Low-Rank Matrix Recovery
Jirong Yi, Weiyu Xu
Low-rank matrix recovery has found many applications in science and engineering such as machine learning, signal processing, collaborative filtering, system identification, and Euc…
Separation-Free Super-Resolution from Compressed Measurements is Possible: an Orthonormal Atomic Norm Minimization Approach
Weiyu Xu, Jirong Yi, Soura Dasgupta +3
We consider the problem of recovering the superposition of distinct complex exponential functions from compressed non-uniform time-domain samples. Total Variation (TV) minimiza…
Fast dose optimization for rotating shield brachytherapy
Myung Cho, Xiaodong Wu, Hossein Dakhah +4
Purpose: To provide a fast computational method, based on the proximal graph solver (POGS) - a convex optimization solver using the alternating direction method of multipliers (ADM…