Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
This addresses security risks in multi-agent AI systems by providing practical design guidance, though it is incremental as it builds on existing leakage concerns with a new measurement framework.
The paper tackled the problem of quantifying how graph topology affects memory leakage in multi-agent LLM systems, finding that denser connectivity, shorter distances, and higher centrality increase leakage, with spatiotemporal attributes leaking more readily than identity credentials.
Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introduce MAMA (Multi-Agent Memory Attack), a framework that measures how network structure shapes leakage. MAMA operates on synthetic documents containing labeled Personally Identifiable Information (PII) entities, from which we generate sanitized task instructions. We execute a two-phase protocol: Engram (seeding private information into a target agent's memory) and Resonance (multi-round interaction where an attacker attempts extraction). Over 10 rounds, we measure leakage as exact-match recovery of ground-truth PII from attacker outputs. We evaluate six canonical topologies (complete, ring, chain, tree, star, star-ring) across $n\in\{4,5,6\}$, attacker-target placements, and base models. Results are consistent: denser connectivity, shorter attacker-target distance, and higher target centrality increase leakage; most leakage occurs in early rounds and then plateaus; model choice shifts absolute rates but preserves topology ordering; spatiotemporal/location attributes leak more readily than identity credentials or regulated identifiers. We distill practical guidance for system design: favor sparse or hierarchical connectivity, maximize attacker-target separation, and restrict hub/shortcut pathways via topology-aware access control.