MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when monitoring the top 10%.
Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthiness concerns: adversarial agents can inject misleading information that propagates contagiously through the system, corrupting benign agents and leading to false outputs. Existing graph-based defenses model agents as nodes and communications as edges, yet are limited to static-graph defenses. In this paper, we propose a dynamic defense paradigm that models MAS communication as a signed directed acyclic graph and computes each agent's contribution to the final decision via backward propagation, enabling accurate identification and isolation of malicious agents to secure multi-agent task collaboration. Experimental results in complex and dynamic MAS environments demonstrate that our method notably outperforms existing MAS defense mechanisms, providing an effective guardrail for trustworthy MAS deployment. Our code is available at https://github.com/ChengcanWu/BPD.
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
KYA provides a framework-agnostic trust layer using inbound pipelines, policy composition, unified trust scoring, interaction multipliers, and delegation attribution to ensure authorized, conforming, and verifiable actions in autonomous systems.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when monitoring the top 10%.
-
KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition
KYA provides a framework-agnostic trust layer using inbound pipelines, policy composition, unified trust scoring, interaction multipliers, and delegation attribution to ensure authorized, conforming, and verifiable actions in autonomous systems.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.