๐Ÿ“–
Correlated Failures of AI Approval Monitors
Luca Zanolini

Correlated Failures of AI Approval Monitors

Author / Organization:
Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined by aggregating scores or by counting approvals, whatever inputs the monitors share. Monitors that share a base model or a poisoned input, however, may fail together. We borrow the fail-prone systems of distributed computing: lists of monitor sets that may fail together. A rule is safe if it executes no bad action and live if it blocks no good one. We measured twelve small open-weights monitors on payment approval under two pre-registered protocols. Without pre-registration, we also measured three closed frontier models (Claude Opus 5.5, GPT-6 Astra, Gemini 4 Argon) and the open DeepSeek-V3.2. Every reliable fooling of a monitor into approving a fraud came through an evidence source and reached only that source's readers. Fooling it into blocking a correct payment depended on injection resistance, a monitor's refusal to follow instructions planted in its data. Small models and DeepSeek obeyed such notes. The three closed models ignored them in all but one case, and Opus also resisted persuasion tailored to it. On new data, a rule that counts sources instead of votes blocked 0.9% of correct payments, against 7.4% for the best counting rule, at equal safety. The pre-registered worst-case test failed. One attack left the approvers on a single source, so no rule over the twelve language-model monitors survives every measured attack. Adding a rule engine, which cannot be persuaded, restored the condition for a safe and live rule on the measured attacks. Diversify the inputs, harden the monitors, count sources, not votes.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title Correlated Failures of AI Approval Monitors
Author / Organization Luca Zanolini
Subject & Discipline cs.CR
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-268149
Original Source Link Visit Source Page on arxiv.org »