BDPL: A boundary differentially private layer against machine learning model extraction attacks

[PDF] arxiv.org

Prediction poisoning: Towards defenses against dnn model stealing attacks

T Orekondy, B Schiele, M Fritz - arXiv preprint arXiv:1906.10908, 2019 - arxiv.org
High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-
world applications eg, cloud prediction APIs. Recent advances in model functionality …
被引用次数：165 相关文章 所有 7 个版本