Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers

arXiv:2406.18451v1 Announce Type: new
Abstract: Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to imperceptible perturbations, creating serious risks when deploying them for high-stakes real-world applications. While detecting such cases may be critical, evaluating a model's vulnerability at a per-instance level using adversarial attacks is computationally too intensive and unsuitable for real-time deployment scenarios. The input space margin is the exact score to …

abstract adversarial adversarial training applications arxiv cases classifiers cs.ai cs.cv cs.lg decisions deep learning deploying free research risks robust robustness strategies them training type while world