TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Khanh Linh, Nghiem, Hoa, Tran, Tu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914446484439040
author Nguyen, Khanh Linh
Nghiem, Hoa
Tran, Tu
author_facet Nguyen, Khanh Linh
Nghiem, Hoa
Tran, Tu
contents AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero safety when the monitor is the same model as the agent (collusion). We present TraceGuard, a structured multi-dimensional monitoring protocol that evaluates agent actions across five dimensions -- goal alignment, constraint adherence, reasoning coherence, safety awareness, and action-trace consistency -- scored in parallel by independent LLM calls, augmented by seven heuristic detectors and an LLM-based intent analyzer. We evaluate on BashArena (637 bash tasks, 4 attack categories) within the ControlArena framework. Our results on 519 samples (279 honest, 240 attack) show that: (1) the hybrid approach achieves clear attack-honest separation (attack mean 0.616 vs. honest mean 0.206, Delta=0.410); (2) structured scoring constrains collusion -- the untrusted structured monitor achieves 95% safety vs. 0% for single-score untrusted monitoring; (3) goal alignment and constraint adherence are the most discriminative dimensions; and (4) a separation-of-duties variant splitting dimensions across trusted and untrusted models achieves 100% safety while preventing any single model from seeing the full evaluation. TraceGuard is implemented as a new monitor type for the open-source ControlArena framework.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03968
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol
Nguyen, Khanh Linh
Nghiem, Hoa
Tran, Tu
Cryptography and Security
Artificial Intelligence
AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero safety when the monitor is the same model as the agent (collusion). We present TraceGuard, a structured multi-dimensional monitoring protocol that evaluates agent actions across five dimensions -- goal alignment, constraint adherence, reasoning coherence, safety awareness, and action-trace consistency -- scored in parallel by independent LLM calls, augmented by seven heuristic detectors and an LLM-based intent analyzer. We evaluate on BashArena (637 bash tasks, 4 attack categories) within the ControlArena framework. Our results on 519 samples (279 honest, 240 attack) show that: (1) the hybrid approach achieves clear attack-honest separation (attack mean 0.616 vs. honest mean 0.206, Delta=0.410); (2) structured scoring constrains collusion -- the untrusted structured monitor achieves 95% safety vs. 0% for single-score untrusted monitoring; (3) goal alignment and constraint adherence are the most discriminative dimensions; and (4) a separation-of-duties variant splitting dimensions across trusted and untrusted models achieves 100% safety while preventing any single model from seeing the full evaluation. TraceGuard is implemented as a new monitor type for the open-source ControlArena framework.
title TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2604.03968