Post-breach Recovery
Shawn Shan, Wenxin Ding, Emily Wenger, Hai-Tao Zheng, Ben Y. Zhao
2022Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security10 citationsDOIOpen Access PDF
Abstract
Server breaches are an unfortunate reality on today's Internet. In the context of deep neural network (DNN) models, they are particularly harmful, because a leaked model gives an attacker "white-box'' access to generate adversarial examples, a threat model that has no practical robust defenses. For practitioners who have invested years and millions into proprietary DNNs, e.g. medical imaging, this seems like an inevitable disaster looming on the horizon.
Topics & Concepts
Computer scienceAdversarial Robustness in Machine LearningAdvanced Malware Detection TechniquesSecurity and Verification in Computing