Towards Scalable and Robust Model Versioning

arXiv:2401.09574v2 Announce Type: replace-cross
Abstract: As the deployment of deep learning models continues to expand across industries, the threat of malicious incursions aimed at gaining access to these deployed models is on the rise. Should an attacker gain access to a deployed model, whether through server breaches, insider attacks, or model inversion techniques, they can then construct white-box adversarial attacks to manipulate the model's classification outcomes, thereby posing significant risks to organizations that rely on these models for critical tasks. …

access arxiv attacker attacks breaches cs.cr cs.lg deep learning deployment industries insider insider attacks malicious server techniques threat versioning