8 papers
Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems
Xiuming Liu, Le Gai, Zhiyuan Chang +4
Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later ag…
Checking Leakage Witnesses versus Certifying Bounded Non-Leakage
Chao Feng, Burkhard Stiller
When a language-model audit finds no leak, what is needed to certify non-leakage? We study guarantees over a declared prompt domain under an executable leakage criterion and decodi…
CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning
Chao Feng, Burkhard Stiller
Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sample-dependent placement may weaken backdoor implantation across aggregation roun…
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
Jiajun Ruan, Peiyang Li, Yukun Chen +2
The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to miti…
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Peiyang Li, Songping Wang, Yi Huang +9
Autonomous AI agents have driven the transition from conversation to task execution, shifting security failures from textual deception to system compromise. Although security evalu…
UnlinkableDFL: A Framework for Network-Layer Unlinkability in Decentralized Federated Learning
Chao Feng, Thomas Grubl, Jan von der Assen +4
Decentralized Federated Learning (DFL) removes the central aggregator of conventional Federated Learning, but peer-to-peer model exchange still exposes network traces: who communic…
DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences
Chao Feng, Yunlong Li, Yuanzhe Gao +4
Federated learning (FL) has garnered significant attention as a prominent privacy-preserving Machine Learning (ML) paradigm. Decentralized FL (DFL) eschews traditional FL's central…
S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning
Pedro Miguel Sánchez Sánchez, Enrique Tomás Martínez Beltrán, Chao Feng +3
Decentralized Federated Learning (DFL) enables collaborative, privacy-preserving model training without relying on a central server. This decentralized approach reduces bottlenecks…