Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused by other agents and amplified into system-level harm. We introduce HARP (Harm Amplification through Role Perturbation), a trace-first methodology for studying local-to-global harm amplification in multi-agent LLM systems. HARP compares paired clean and perturbed executions and records specialist outputs, tool calls, memory reads/writes, guard events, oracle logs, latency, token cost, and decisions. We define local harm as deviation from targeted agents or corrupted channels, global harm as deviation over the full trace, and harm amplification as (H_global/H_local). This complements attack success rate with a measure of how strongly orchestration spreads harm beyond the attack point. We instantiate HARP in a finance-oriented seven-agent system with a deterministic decision gate and configurable attack harness for specialist compromise, collusion, shared-context corruption, and temporal or memory-persistent attacks. Across five defenses, prompt-only defenses preserve benign utility but leave high success and stealth; pre-tool and step-level guards reduce some failures with utility or latency costs; and IntegrityGuard, a trace-consistency defense, achieves the lowest attack success and global harm but introduces utility/cost trade-offs. Results show that single-specialist compromise produces the strongest amplification, shared-context corruption yields the highest attack success, and temporal persistence produces the largest malicious impact. HARP argues that secure multi-agent evaluation must measure not only bypass, but propagation.

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and from 100% to 55.6% on Gemini 2.0 Flash. We formalize this as the Camouflage Detection Gap (CDG), the difference in injection detection rate between static and camouflaged payloads. Across 45 tasks spanning three domains and two model families, CDG is large and statistically significant (chi^2 = 38.03, p < 0.001 for Llama; chi^2 = 17.05, p < 0.001 for Gemini), with zero reverse discordant pairs in either case. We additionally evaluate Llama Guard 3, a production safety classifier, which detects zero camouflage payloads (IDRcamouflage = 0.000), confirming that the blind spot extends beyond few-shot detectors to dedicated safety classifiers. We further show that multi-agent debate architectures amplify static injection attacks by up to 9.9x on smaller models, while stronger models show collective resistance. Targeted detector augmentation provides only partial remediation (10.2% improvement on Llama, 78.7% on Gemini), suggesting the vulnerability is architectural rather than incidental for weaker models. Our framework, task bank, and payload generator are released publicly.