Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors

• URL: http://arxiv.org/abs/2607.07368v1
• Date: Wed, 08 Jul 2026 13:03:25 GMT
• Title: Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
• Abstract summary: We study multi-agent AI control, formalising distributed attacks in which several agents jointly aim for a malicious goal.<n>We develop FakeLab: a synthetic AI-lab (9 services, 86 benign tasks, 4 attack objectives)<n>Our central finding is the fragmentation effect: as more agents coordinate to attack, per-agent monitoring becomes less likely to catch any of the attackers.
• Score: 4.246803713067298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one trajectory, but real deployments run many agents over shared infrastructure, and the most severe risks (model-weight exfiltration, training-run poisoning) plausibly need several agents acting in concert. We initiate the empirical study of multi-agent AI control, formalising distributed attacks in which several agents jointly aim for a malicious goal. We develop FakeLab: a synthetic AI-lab codebase (9 services, 86 benign tasks, 4 attack objectives). We evaluate single agent monitoring against distributed attacks, varying the number of agents, their coordination, model capabilities and precise monitoring configuration. Our central finding is the fragmentation effect: as more agents coordinate to attack, per-agent monitoring becomes less likely to catch any of the attackers. Secondly, this is not driven by the ratio of benign to malicious code -- we argue this is likely dependent on model capability. Third, an explicit planner amplifies the fragmentation effect, raises the rate of completing the attack up to sevenfold, and mildly sharpens executors' poor monitor-theory-of-mind. Finally: a weak "trusted" monitor misses most attacks, while a stronger one cuts undetected success by more than an order of magnitude but remains imperfect. We are happy to share FakeLab, our control setting, with safety researchers on request.

Related papers

• OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage [59.3826294523924]
  We investigate the security vulnerabilities of a popular multi-agent pattern known as the orchestrator setup.<n>We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable.
  arXiv  Detail & Related papers  (2026-02-13T21:32:32Z)
• Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks [12.356708678431183]
  Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought (CoT) and tool-use actions to ensure alignment with user intent.<n>We demonstrate that these monitoring-based defenses can be bypassed via a novel Agent-as-a- Proxy attack.<n>Our findings suggest current monitoring-based agentic defenses are fundamentally fragile regardless of model scale.
  arXiv  Detail & Related papers  (2026-02-04T21:38:38Z)
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols [80.68060125494645]
  We study adaptive attacks by an untrusted model that knows the protocol and the monitor model.<n>We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs.
  arXiv  Detail & Related papers  (2025-10-10T15:12:44Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems [25.6233463223145]
  We study intention-hiding threats in multi-agent systems powered by Large Language Models (LLM-MAS)<n>We design four representative attack paradigms that subtly disrupt task completion while maintaining a high degree of stealth.<n>To counter these threats, we propose AgentXposed, a psychology-inspired detection framework.
  arXiv  Detail & Related papers  (2025-07-07T07:34:34Z)
• Ctrl-Z: Controlling AI Agents via Resampling [2.505902477669827]
  We construct BashBench, a dataset of 257 challenging multi-step system administration tasks.<n>We evaluate whether various safety measures can prevent an adversarially constructed AI agent from covertly downloading and executing malicious code.
  arXiv  Detail & Related papers  (2025-04-14T16:22:11Z)
• MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents [60.30753230776882]
  LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions.<n>We present MELON, a novel IPI defense that detects attacks by re-executing the agent's trajectory with a masked user prompt modified through a masking function.
  arXiv  Detail & Related papers  (2025-02-07T18:57:49Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.