52 citations · 204 across the 12 of their papers we have counts for
4 papers · 1 filter
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Guangyu Shen, Yingqi Liu, Guanhong Tao +5
Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger suc…
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
Siyuan Cheng, Yingqi Liu, Shiqing Ma +1
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor…
Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
Yongqiang Tian, Shiqing Ma, Ming Wen +3
Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inf…
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
Guanhong Tao, Shiqing Ma, Yingqi Liu +1
Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attac…