3 papers
cs.CR2026
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…
cs.CR2025
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…
cs.CR2025
3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
Jianyao Yin, Luca Arnaboldi, Honglong Chen +2
Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while…