5 papers
Stateful Agent Backdoor
Zhengchunmin Dai, Jiaxiong Tang, Liantao Wu +2
Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that e…
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…
Sigil: Server-Enforced Watermarking in U-Shaped Split Federated Learning via Gradient Injection
Zhengchunmin Dai, Jiaxiong Tang, Peng Sun +2
In decentralized machine learning paradigms such as Split Federated Learning (SFL) and its variant U-shaped SFL, the server's capabilities are severely restricted. Although this en…
Robust Client-Server Watermarking for Split Federated Learning
Jiaxiong Tang, Zhengchunmin Dai, Liantao Wu +3
Split Federated Learning (SFL) is renowned for its privacy-preserving nature and low computational overhead among decentralized machine learning paradigms. In this framework, clien…
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…