ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents
Organizations: University College of Engineering, BIT Campus, Anna University, Tiruchirappalli 620 024, India · Department of Computer Applications, National Institute of Technology Tiruchirappalli, Tiruchirappalli 620 015, India
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.
Figures & tables
| (cycles) | clean escalation | added cost/decision | covert FA | |
|---|---|---|---|---|
| 0.01 | 0.000 | $0.00 | 1.000 | |
| 0.05 | 18.2 | 0.030 | $1.33 | 0.868 |
| 0.10 | 15.2 | 0.064 | $2.90 | 0.840 |
| 0.20 | 10.8 | 0.165 | $7.44 | 0.775 |
| Clean | Attack success rate | Utility | |||||
| Configuration | err | abst | A1-a | A1-b | A2 | A3 | A1-a |
| Undefended ReAct | 0.68 | n/a | 0.39 | 0.76 | 0.00 | 0.52 | 0.32 |
| Defensive prompt only | 0.41 | n/a | 0.29 | 0.18 | 0.54 | 0.67 | 0.48 |
| Spotlighting | 0.68 | n/a | 0.39 | 0.77 | 0.00 | 0.51 | 0.31 |
| Adversarial training | 0.41 | n/a | 0.29 | 0.18 | 0.04 † | n/a | 0.48 |
| Provenance monitor | 0.41 | 0.00 | 0.29 | 0.00 | 0.54 | 0.67 | 0.48 |
| Defence | clean escalation | fixed A2 | adaptive |
|---|---|---|---|
| None | 0.000 | 0.702 | n/a |
| Adversarial training | n/a | 0.037 | 0.485 |
| Width-based conformal | 0.050 | 0.235 | 0.925 |
| Mahalanobis OOD | 0.019 | 0.000 | 0.504 |
| Physics clock ( ) | 0.027 | 0.006 | 0.046 |
| Monitor | clean escalation | suppression | false alarm | |
|---|---|---|---|---|
| Static support | 0.004 | 0.151 | 0.529 | 1.02, 1.02 |
| Clock, | 0.034 | 0.005 | 0.033 | 1.44, 1.40 |
| Clock, | 0.030 | 0.000 | 0.049 | 1.18, 1.30 |
| Clock, | 0.027 | 0.000 | 0.046 | 1.00, 1.00 |
| Per-window | Proposition 1 | |||||||
| Data | Monitor | pooled | mean | p90 | pooled | mean | p90 | |
| FD001, 100 engines | static support | 0.058 | 0.058 | 0.124 | 1.02, 1.02 | 0.004 | 0.004 | 0.000 |
| clock, | 0.140 | 0.115 | 0.334 | 1.44, 1.40 | 0.034 | 0.030 | 0.084 | |
| clock, | 0.077 | 0.065 | 0.194 | 1.18, 1.30 | 0.030 | 0.027 | 0.092 | |
| clock, | 0.027 | 0.023 | 0.076 | 1.00, 1.00 | 0.027 | 0.023 | 0.076 | |
| FD004, 248 engines | static support | 0.061 | 0.059 | 0.196 | 1.02, 1.02 | 0.000 | 0.000 | 0.000 |
| Per-window | Proposition 1 | Covert reach | ||||||
|---|---|---|---|---|---|---|---|---|
| Pattern | Observed | mean | worst | mean | worst | per-window | Prop. 1 | |
| Smooth | truncated | 0.046 | 0.072 | 1.09 | 0.034 | 0.055 | 0.049 | 0.055 |
| Noisy | truncated | 0.031 | 0.040 | 1.03 | 0.027 | 0.036 | 0.266 | 0.285 |
| Abrupt onset | truncated | 0.023 | 0.045 | 1.04 | 0.021 | 0.045 | 0.631 | 0.659 |
| Switching regimes | truncated | 0.038 | 0.074 | 1.08 | 0.027 | 0.046 | 0.049 | 0.055 |
| Rate mismatch | truncated | 0.030 | 0.041 | 1.03 | 0.026 | 0.041 | 0.036 | 0.038 |
| Attack | Monitor | caught before harm | FA success |
|---|---|---|---|
| Universal perturbation | static support | 0.000 | 1.000 |
| clock, | 1.000 | 0.142 | |
| Adaptive, non-covert | static support | 0.000 | 1.000 |
| clock, | 1.000 | 0.138 | |
| Adaptive, covert, persistent | static support | 0.000 | 1.000 |
| clock, | 0.000 | 0.638 |
| Suppression | False alarm | ||||
|---|---|---|---|---|---|
| Dataset | clean abst | static | clock | static | clock |
| C-MAPSS FD001 | 0.027 | 0.151 | 0.000 | 0.529 | 0.046 |
| C-MAPSS FD004 | 0.030 | 0.808 | 0.099 | 0.221 | 0.038 |
| MetroPT-3 | 0.075 | 0.500 | 0.183 | 0.998 | 0.104 |
| , clean | trig. | Clean abst | A1-a ASR | |||
|---|---|---|---|---|---|---|
| Planner | all | worst | under A2 | after retry | prompt | |
| Qwen3-14B | 0.410 | 0.723 | 0.340 | 0.000 | 0.287 | 0.000 |
| Phi-4-14B | 0.500 | 1.000 | 0.393 | 0.000 | 0.013 | 0.000 |
| Gemma-3-12B | 0.627 | 0.864 | 0.820 | 0.000 | 0.117 | 0.000 |
| Mistral-Nemo-12B | 0.648 | 1.000 | 0.703 | 0.000 | 0.090 | 0.000 |
| Llama-3.1-8B | 0.456 | 0.907 | 0.360 | 0.000 | 0.310 | 0.000 |
AI Agent Security
Artificial intelligence agent security studies attacks and safeguards for tool-using, persistent, and collaborative systems across digital and physical settings.
See all 563 papers