2023/08/01 by Elvis Dohmatob, Dohmatob, Elvis, Meyer Scetbon +1 · 1 citation
Computer Science · Agricultural and Biological Sciences · Engineering · #Adversarial Robustness in Machine Learning #Pesticide Residue Analysis and Safety #Fault Detection and Control Systems
paper · pdf · doi:10.48550/arxiv.2308.00556
In this paper, we investigate the impact of test-time adversarial attacks on linear regression models and determine the optimal level of robustness that any model can reach while maintaining a given level of standard predictive performance (accuracy). Through quantitative estimates, we uncover fundamental tradeoffs between adversarial robustness and accuracy in different regimes. We obtain a precise characterization which distinguishes between regimes where robustness is achievable without hurting standard accuracy and regimes where a tradeoff might be unavoidable. Our findings are empirically confirmed with simple experiments that represent a variety of settings. This work applies to feature covariance matrices and attack norms of any nature, and extends beyond previous works in this area.