홈 › Papers

Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs

Multi-agent deployments of large language models (LLMs) are increasingly embedded in market, allocation, and governance workflows, yet covert coordination among agents can silently erode trust and social welfare. Existing audits are dominated by heuristics that lack theoretical guarantees, struggle to transfer across tasks, and seldom ship with the infrastructure needed for independent replication. We introduce Audit the Whisper, a conference-grade research artifact that spans theory, benchmark design, detection, and reproducibility. Our contributions are: (i) a channel-capacity analysis showing how interventions such as paraphrase, rate limiting, and role permutation impose quantifiable capacity penalties-operationalised via paired-run Kullback--Leibler diagnostics-that tighten mutual-information thresholds with finite-sample guarantees and full proofs; (ii) ColludeBench-v0, covering pricing, first-price auctions, peer review, and hosted Gemini/Groq APIs with configurable covert schemes, deterministic manifests, and reward instrumentation; and (iii) a calibrated auditing pipeline that fuses cross-run mutual information, permutation invariance, watermark variance, and fairness-aware acceptance bias, each tuned to a $10^{-3}$ false-positive budget and validated by 10k honest runs plus an e-value martingale. Across ColludeBench and external suites including Secret Collusion, CASE, Perfect Collusion Benchmark, and SentinelAgent, the union meta-test attains state-of-the-art power at fixed FPR while ablations surface price-of-auditing trade-offs and fairness-driven colluders invisible to MI alone. We release regeneration scripts, anonymized manifests, and documentation so that external auditors can reproduce every figure, satisfy double-blind requirements, and extend the framework with minimal effort.

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반