5 papers
Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models
Junjian Li, Xiaolong Liu, Peng Sun +4
Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I) diffusion models. Existing defenses typically detect backdoors from specific abnormal pattern…
Stateful Agent Backdoors: Constructing Cross-Session Attack Programs
Zhengchunmin Dai, Jiaxiong Tang, Liantao Wu +5
Multi-step attacks on large language model agents may depend on opportunities distributed across sessions, such as access to target information or the availability of required tool…
Server-Enforced Watermarking in U-Shaped Split Federated Learning
Zhengchunmin Dai, Jiaxiong Tang, Peng Sun +2
U-shaped split federated learning (U-SFL) enables resource-constrained Internet of Things devices to collaboratively train models with an edge server while retaining raw data and l…
FFCBA: Feature-based Full-target Clean-label Backdoor Attacks
Yangxu Yin, Honglong Chen, Yudong Gao +4
Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintai…
SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
Yangxu Yin, Honglong Chen, Yudong Gao +3
Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows…