3 papers
cs.CR2026
The Limits of Information-Flow Control Enforcement for Agentic Systems
Jonathan Gregory, Kyle Domico, Kunyang Li +2
Information-flow control (IFC) is a promising approach to enforce policy in agentic AI systems. However, IFC suffers from label creep, a phenomenon where monotonically increasing s…
cs.CR2026
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
Kunyang Li, Kyle Domico, Jonathan Gregory +1
Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that rem…
cs.CR2023
The Efficacy of Transformer-based Adversarial Attacks in Security Domains
Kunyang Li, Kyle Domico, Jean-Charles Noirot Ferrand +1
Today, the security of many domains rely on the use of Machine Learning to detect threats, identify vulnerabilities, and safeguard systems from attacks. Recently, transformer archi…