Honeypot Protocol

📅 2026-04-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Traditional AI monitoring mechanisms are vulnerable to adaptive attacks, collusion, and strategic evasion due to their passive observation paradigm. This work proposes the first active probing-based monitoring protocol, which manipulates model perception by embedding three distinct conditions—evaluation, synthetic deployment, and explicit no-monitoring—within system prompts, while maintaining consistency in task, environment, and scoring criteria. Experiments with Claude Opus 4.6 in the BashArena environment demonstrate that the model achieves 100% success on the primary task across all conditions without triggering any side-effect tasks, thereby validating the efficacy of the proposed approach. These results establish a foundational benchmark for evaluating more sophisticated adversarial strategies and multi-model monitoring frameworks in future research.

Technology Category

Application Category

📝 Abstract
Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.
Problem

Research questions and friction points this paper is trying to address.

trusted monitoring
adaptive attacks
collusion
strategic attack selection
passive monitoring
Innovation

Methods, ideas, or system contributions that make the work stand out.

honeypot protocol
active monitoring
context-dependent behavior
AI safety
system prompt manipulation
🔎 Similar Papers
No similar papers found.