Stateful Online Monitoring Catches Distributed Agent Attacks

• URL: http://arxiv.org/abs/2605.31593v1
• Date: Fri, 29 May 2026 17:57:00 GMT
• Title: Stateful Online Monitoring Catches Distributed Agent Attacks
• Abstract summary: We develop an online stateful monitor that uses real-time clustering to collect weak suspiciousness signals across many agent transcripts.<n>Our results point toward a new class of safety monitors which reason over groups of users rather than isolated transcripts.
• Score: 63.00394432922707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection, attackers frequently distribute their misuse, splitting a harmful task across many user accounts so each individual transcript looks benign. Because safety monitors score only one agent context at a time, they are structurally blind to misuse that is only visible in aggregate, across many accounts. We show this gap is real by building, to our knowledge, the first distributed agent attack, a multi-agent scaffold that completes hard cybersecurity tasks while hiding the harmful objective across subagents with limited contexts, evading a standard monitor that catches it only a fifth as often as prior agent attacks. Towards a defense, we develop an online stateful monitor that uses real-time clustering to collect weak suspiciousness signals across many agent transcripts, and escalates only rarely to a language model that flags misuse across user accounts. In evaluations with large-scale simulated datacenter traffic, our monitor Pareto dominates standard monitors, catching distributed attacks 30% earlier and flagging cyber misuse before it reaches the most harmful stages. Crucially, this comes at negligible additional latency for ~99% of user traffic. This detection advantage persists but narrows as the benign background traffic grows very large. After an extensive red-teaming exercise, we improve the defense and surprisingly also find that it catches standard jailbreaks, since adaptive attackers reuse attack variants across accounts. Our results point toward a new class of safety monitors which reason over groups of users rather than isolated transcripts.

Related papers

• Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors [4.246803713067298]
  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.
  arXiv  Detail & Related papers  (2026-07-08T13:03:25Z)
• SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors [3.989565392866092]
  We present SLEIGHT-Bench (Subtle Low-itEration Insight-Guided Harmful Transcripts), a benchmark of synthetic transcripts containing 40 attacks across 11 categories.<n>We find that 20 of 40 attacks are never caught by an Opus 4.6 monitor with extended thinking across 10 trials at a 1% false-positive rate, while the overall catch rate is 32%.
  arXiv  Detail & Related papers  (2026-05-15T20:46:46Z)
• 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)
• Async Control: Stress-testing Asynchronous Control Measures for LLM Agents [2.7146936326590425]
  We investigate asynchronous monitoring, in which a monitoring system reviews agent actions after the fact.<n>Unlike synchronous monitoring, this approach does not impose runtime latency, while still attempting to disrupt attacks before irreversible harm occurs.<n>We treat monitor development as an adversarial game between a blue team (who design monitors) and a red team (who create sabotaging agents)
  arXiv  Detail & Related papers  (2025-12-15T16:56:28Z)
• 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)
• Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents [54.35629963816521]
  This work introduces VIBMA, the first clean-text backdoor attack targeting VLM-based mobile agents.<n>The attack injects malicious behaviors into the model by modifying only the visual input.<n>We show that our attack achieves high success rates while preserving clean-task behavior.
  arXiv  Detail & Related papers  (2025-06-16T08:09:32Z)
• 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)
• Backdoor Attack against Speaker Verification [86.43395230456339]
  We show that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data. We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
  arXiv  Detail & Related papers  (2020-10-22T11:10:08Z)

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.