activity
20182021
most citedA Backdoor Attack against 3D Point Cloud Classifiers

6 citations · 6 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CR2021

Detecting Backdoor Attacks Against Point Cloud Classifiers

Zhen Xiang, David J. Miller, Siheng Chen +2

Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a s…

cs.CR20216 cited

A Backdoor Attack against 3D Point Cloud Classifiers

Zhen Xiang, David J. Miller, Siheng Chen +2

Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks agains…

cs.CV2020

L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set

Zhen Xiang, David J. Miller, George Kesidis

Backdoor attacks (BAs) are an emerging form of adversarial attack typically against deep neural network image classifiers. The attacker aims to have the classifier learn to classif…

cs.LG2020

Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing

Zhen Xiang, David J. Miller, George Kesidis

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively sma…

stat.ML2019

Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers

George Kesidis, David J. Miller, Zhen Xiang

We provide a new local class-purity theorem for Lipschitz continuous DNN classifiers. In addition, we discuss how to achieve classification margin for training samples. Finally, we…

cs.LG2019

Detection of Backdoors in Trained Classifiers Without Access to the Training Set

Zhen Xiang, David J. Miller, George Kesidis

Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade clas…