3 papers
cs.CR2024
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
Haiyang Yu, Tian Xie, Jiaping Gui +3
Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural network…
cs.LG2024
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective
Nan Li, Haiyang Yu, Ping Yi
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be er…
cs.LG2023
OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection
Haoyu Jiang, Haiyang Yu, Nan Li +1
Deep neural networks (DNNs) have been found vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. There are various app…