Research
Adversarial Training of Linear Models under Stealthy Attacks
arXiv:2608.25681v1 Announce Type: new Abstract: Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial
arXiv:2608.25681v1 Announce Type: new Abstract: Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial training have been proposed, but such approaches lack guarantees against stealthy attacks. We therefore propose a detector-based switched model, in which optimal attack strategies are stealthy. For linear prediction models, we derive a convex formulation of the resulting adversarial risk. The model incorporates protected features and introduces a hyperparameter modelling attack probability, enabling an explicit performance trade-off between clean and attacked data regimes. Numerical simulations on real and synthetic data show improved performance on partially attacked data, even for misspecified attack probabilities.
Related
- Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
- Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks
- Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems
Source: arXiv cs.LG | 2026-08-27