Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Khaled, Kacem"'
Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The current s
Externí odkaz:
http://arxiv.org/abs/2309.01838
Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to secure model
Externí odkaz:
http://arxiv.org/abs/2207.10561