cs.CRcs.AIcs.MA

GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systems

Pablo Mateo-Torrejón, Alfonso Sánchez-Macián

Apr 27, 2026

AI Summarygemma4:e4b

The paper introduces Gammaf, an open-source benchmarking framework designed to standardize the evaluation of graph-based anomaly detection methods for securing Large Language Model Multi-Agent Systems.

Abstract

More Like This

The rapid integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) has significantly enhanced their collaborative problem-solving capabilities, but it has also expanded their attack surfaces, exposing them to vulnerabilities such as prompt infection and compromised inter-agent communication. While emerging graph-based anomaly detection methods show promise in protecting these networks, the field currently lacks a standardized, reproducible environment to train these models and evaluate their efficacy. To address this gap, we introduce Gammaf (Graph-based Anomaly Monitoring for LLM Multi-Agent systems Framework), an open-source benchmarking platform. Gammaf is not a novel defense mechanism itself, but rather a comprehensive evaluation architecture designed to generate synthetic multi-agent interaction datasets and benchmark the performance of existing and future defense models. The proposed framework operates through two interdependent pipelines: a Training Data Generation stage, which simulates debates across varied network topologies to capture interactions as robust attributed graphs, and a Defense System Benchmarking stage, which actively evaluates defense models by dynamically isolating flagged adversarial nodes during live inference rounds. Through rigorous evaluation using established defense baselines (XG-Guard and BlindGuard) across multiple knowledge tasks (such as MMLU-Pro and GSM8K), we demonstrate Gammaf's high utility, topological scalability, and execution efficiency. Furthermore, our experimental results reveal that equipping an LLM-MAS with effective attack remediation not only recovers system integrity but also substantially reduces overall operational costs by facilitating early consensus and cutting off the extensive token generation typical of adversarial agents.

The paper introduces ACIArena, a unified and comprehensive evaluation framework…

02Low24%

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions

The paper develops a novel attack method for multi-agent discussions under conti…

03Low21%

Agent Audit: A Security Analysis System for LLM Agent Applications

Agent Audit is a novel security analysis system that comprehensively audits LLM…

04Low20%

The Autonomy Tax: Defense Training Breaks LLM Agents

Defense training for LLM agents, intended to improve safety, systematically degr…

05Low18%

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks

CoopGuard is a novel stateful, multi-round defense framework using cooperative a…

06Low18%

Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning

The paper introduces C-MADF, a causally constrained multi-agent framework that s…

07Low17%

DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns

DeepStage is a deep reinforcement learning framework that achieves autonomous, s…

08Low16%

Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs

The paper proposes TAGBD, a graph-aware backdoor attack that demonstrates that i…