AI & ML
ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents
arXiv cs.CR0 views
arXiv:2611.22288v1 Announce Type: cross Abstract: Large-language-model agents now close the industrial predictive-maintenance loop, reading sensor windows, retrieving procedures and dispatching work orders. Two attack channels meet there: injected text in a retrieved document can hijack the decision, and a bounded sensor perturbation can corrupt the remaining-useful-life estimate behind it. Recent agent defenses police data provenance and tool privilege but cannot tell whether a prognostic quantity is physically plausible. ConfGuard is a reference monitor with a physics-grounded policy. Its conformal monitor tests each prediction, anchored to the asset's admitted history, against degradation physics: capped remaining life never rises and falls at most one cycle per cycle. Calibrating its threshold over whole asset trajectories lets the operator set the expected share of a clean asset's windows the running monitor escalates. A physics-policy validator checks the agent's maintenance-urgency decision against the decision a deterministic policy derives from the same interval. On all 10,196 C-MAPSS test windows the monitor cuts a covert attacker's reach on healthy assets from 0.529 to 0.046 and closes suppression of failing assets (0.151 to 0), escalating 0.027 of clean windows against a 0.05 target, while the fixed physical range it replaces leaves both attacks open. Behind a Qwen3-14B planner the composed monitors hold urgency-class injection to 0.00 and the universal sensor attack to 0.12, against 0.29 and 0.54 for a defended prompt. An adaptive attacker defeats a Mahalanobis detector on 0.504 of windows and adversarial training on 0.485. We report an attack class the projection misses.
Source:https://arxiv.org/abs/2611.22288PreviousGuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based RecommendationNextA Little Advice Suffices: Diffie-Hellman Is as Hard as Discrete Logarithm
Related posts
Evidence for late Middle Pleistocene <i>Homo erectus</i> in mainland East Asia
0Nature News
AI must be held accountable — value statements won’t protect human dignity
0Nature News

iOS 27.3 adds Siri AI usage limits, here’s what counts toward your limit
09to5Mac

One UI 9.5 Beta is out now for these Galaxy devices – how to install it
09to5Google
Criminals Have a New Favorite ‘Point-and-Shoot’ AI Hacking Tool
0Wired

GTA 6 Leads The Game Awards 2026 Nominees With 8 Nods Before Launch: Key Craft & Gamedev Takeaways
0dev.to