3 citations · 3 across the 6 of their papers we have counts for
4 papers · 1 filter
Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1
Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across sev…
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
Yibo Hu, Ren Wang
As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundam…
MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
Hyo Seo Kim, Gang Luo, Can Chen +3
Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover opera…
Watermarking Graph Neural Networks via Explanations for Ownership Protection
Jane Downer, Yingdan Shi, Ziyan Liu +2
Graph Neural Networks (GNNs) are widely deployed in industry, making their intellectual property valuable. However, protecting GNNs from unauthorized use remains a challenge. Water…