Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a detector-based switched model to enhance the robustness of linear predictive models against stealthy false data injection attacks. By deriving a convex formulation of adversarial risk that incorporates protected features and a hyperparameter for attack probability, the authors provide a framework that explicitly balances performance between clean and attacked data regimes. Numerical simulations demonstrate that this approach significantly improves performance on partially attacked data, even when attack probabilities are misspecified.
Stealthy attacks can compromise predictive models, but a new switched model shows improved resilience by explicitly modeling attack probabilities.
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.