5 papers
Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling
Zixuan Zhu, Rui Wang, Lihua Jing +1
Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data…
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
Ming Sun, Rui Wang, Xingrui Yu +5
Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As trained VLAs are increasingly…
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
Ming Sun, Lihua Jing, Zixuan Zhu +1
Backdoor attacks pose a significant threat to the training process of deep neural networks (DNNs). As a widely-used DNN-based application in real-world scenarios, face recognition…
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data
Zixuan Zhu, Rui Wang, Cong Zou +1
Recently, backdoor attacks have posed a serious security threat to the training process of deep neural networks (DNNs). The attacked model behaves normally on benign samples but ou…
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
Lihua Jing, Rui Wang, Wenqi Ren +2
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods, which rely on attack data or pri…