ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

• URL: http://arxiv.org/abs/2607.19430v1
• Date: Mon, 20 Jul 2026 19:11:17 GMT
• Title: ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
• Abstract summary: We present ChannelGuard, a framework placing information-bottleneck gates on every inter-agent channel.<n>ChannelGuard blocks Tool Poisoning 30 of 30 at the application layer, identically across Azure GPT-5, Anthropic Sonnet 4.5, and Anthropic Haiku 4.5.<n>It also lowers Prompt Injection attack success by half (0.333 to 0.167) and preserves GSM8K accuracy exactly (0.867)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions. Existing defenses guard only the input boundary (IBProtector, Llama Guard, perplexity filters, SmoothLLM) or run outside the application as opaque, stochastic provider-side filters. We show this gap carries a consequence rarely measured: on a 2,100-trace evaluation across eight attack families, five defenses, and three model backends, an undefended pipeline that appears fully safe under standard reporting (attack success 0.000 on tool- and memory-poisoning) owes that safety almost entirely to the cloud provider's server-side filter (54 of 60 blocks on Azure GPT-5), and silently shifts to the agent model's own alignment on a backend without such a filter. Outcome-only reporting hides this dependence. We present ChannelGuard, a training-free defense-in-depth framework placing information-bottleneck gates on every inter-agent channel; each scores channel text against an adversarial phrase bank by embedding similarity and deterministically passes, compresses, or blocks it, adding no LLM call, while an attribution method records which layer stopped each attack. ChannelGuard's tool-output gate blocks Tool Poisoning 30 of 30 at the application layer, identically across Azure GPT-5, Anthropic Sonnet 4.5, and Anthropic Haiku 4.5, whereas the undefended pipeline shifts entirely across backends; it also lowers Prompt Injection attack success by half (0.333 to 0.167) and preserves GSM8K accuracy exactly (0.867). White-box adaptive paraphrase evades every embedding gate, where a perturb-and-vote baseline does better. An extended appendix adds baselines, ablations, sweeps, a benign-preservation analysis, and a judge audit (kappa = 0.900), at a total cost of 47.36 USD.

Related papers

• Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning [67.04448659688579]
  FGLGuard cuts AgentDojo's ground-success rate by 43% at near-unguarded utility, zero API cost, and negligible capability loss.<n>Federation is not optional: off-the-shelf transfer collapses under distribution shift.<n>Live FGLGuard cuts AgentDojo's ground-success rate by 43% at near-unguarded utility, zero API cost, and negligible capability loss.
  arXiv  Detail & Related papers  (2026-09-02T07:57:12Z)
• The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using Agents [2.45357121165634]
  A tool-using LLM agent that reads attacker-controlled web content faces indirect prompt injection.<n>Ten overt injection classes are refused (gpt-4o 0%), but reframing the identical leak as a mandatory integrity signature.<n>An ablation shows the mechanism is instruction/data confusion, not defeated alignment.
  arXiv  Detail & Related papers  (2026-08-27T13:12:03Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots [1.948261185683419]
  We present a three-layer framework that intercepts both direct and indirect prompt injection throughout the inference pipeline.<n> Evaluation on 5,080 samples across GPT-4o, Llama 3, and Mistral 7B shows that the framework reduces Attack Success Rate (ASR) from 71.4% to 11.3%.
  arXiv  Detail & Related papers  (2026-06-17T23:59:57Z)
• Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing [51.56484100374058]
  Production LLM applications stack several defense families -- refusal-phrase filters, tokenbudget controls, model allowlists, rate limits, tool-registry authentication -- yetBAS benchmarks report a single aggregate coverage number.<n>We add four-LLM-Top-10-aware agents to a 21-agent baseline scanner and target a lattice of four synthetic LLM endpoints.
  arXiv  Detail & Related papers  (2026-06-01T19:39:25Z)
• 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)
• AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents [4.36595961990666]
  AgentShield is a deception-based detection framework.<n>It places three layers of traps inside the agent's tool interface.<n>It catches 90.7%-100% of such successful attacks, with zero false alarms on 485 normal-use tests.
  arXiv  Detail & Related papers  (2026-05-10T20:08:27Z)
• Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models [5.937023024175801]
  We introduce Layerwise Convergence Fingerprinting (LCF), a tuning-free runtime monitor that treats the inter-layer hidden-state trajectory as a health signal.<n> evaluated on four architectures (Llama-3-8B, Qwen2.5-7B, Gemma-2-9B, Qwen2.5-14B) across backdoors, jailbreaks, and prompt injection.
  arXiv  Detail & Related papers  (2026-04-27T14:38:31Z)
• AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations [38.49666480491258]
  LLM agents are highly vulnerable to Indirect Prompt Injection (IPI)<n>We propose a new paradigm, action-level causal attribution, which secures agents by asking why a particular tool call is produced.<n>We instantiate this paradigm with AttriGuard, a runtime defense based on parallel counterfactual tests.
  arXiv  Detail & Related papers  (2026-03-11T13:23:46Z)
• TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking [52.72486831074384]
  Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs.<n>We propose TrapSuffix, a lightweight fine-tuning approach that injects trap-aligned behaviors into the base model without changing the inference pipeline.<n>Across diverse suffix-based jailbreak settings, TrapSuffix reduces the average attack success rate to below 0.01 percent and achieves an average tracing success rate of 87.9 percent.
  arXiv  Detail & Related papers  (2026-02-06T11:43:56Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• 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)
• Denial-of-Service Poisoning Attacks against Large Language Models [64.77355353440691]
  LLMs are vulnerable to denial-of-service (DoS) attacks, where spelling errors or non-semantic prompts trigger endless outputs without generating an [EOS] token. We propose poisoning-based DoS attacks for LLMs, demonstrating that injecting a single poisoned sample designed for DoS purposes can break the output length limit.
  arXiv  Detail & Related papers  (2024-10-14T17:39:31Z)

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.