Research
Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks
arXiv:2604.11410v1 Announce Type: new Abstract: We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern
arXiv:2604.11410v1 Announce Type: new Abstract: We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern-day, complex perception pipelines as bipartite graphs, which combined with anomaly detector alerts defines a Bayesian network for inferring compromised sensors. An active probing strategy exploits system nonlinearities to maximize distinguishability between attack hypotheses, while compromised sensors are selectively disabled to maintain reliable state estimation. We propose a threshold-based probing strategy and show its effectiveness via a simplified partially observable Markov decision process (POMDP) formulation. Experiments on an inverted pendulum under single and multi-sensor attacks show that our method significantly outperforms outlier-robust and prediction-based baselines, especially under prolonged attacks.
Related
- Loss-Driven Bayesian Active Learning
- Zero-Shot Function Encoder-Based Differentiable Predictive Control
- Controller Design for Structured State-space Models via Contraction Theory
- Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
- IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing
Source: arXiv cs.LG | 2026-04-14