# Feasibility of Randomized Detector Tuning for Attack Impact Mitigation

arXiv: https://arxiv.org/abs/2503.11417 · HTML: https://mlsanity.com/paper/2503.11417/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2025.

## Built on by (most cited first, 1 of 1)

- [Adversarial Robustness of Deep State Space Models for Forecasting](https://mlsanity.com/paper/2604.03427/) (2026)

## Abstract (arXiv)

This paper considers the problem of detector tuning against false data injection attacks. In particular, we consider an adversary injecting false sensor data to maximize the state deviation of the plant, referred to as impact, whilst being stealthy. To minimize the impact of stealthy attacks, inspired by moving target defense, the operator randomly switches the detector thresholds. In this paper, we theoretically derive the sufficient (and in some cases necessary) conditions under which the impact of stealthy attacks can be made smaller with randomized switching of detector thresholds compared to static thresholds. We establish the conditions for the stateless (chi2) and the stateful (CUSUM) detectors. The results are illustrated through numerical examples.