MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction

arXiv:2403.18580v1 Announce Type: new
Abstract: The rise of Machine Learning as a Service (MLaaS) has led to the widespread deployment of machine learning models trained on diverse datasets. These models are employed for predictive services through APIs, raising concerns about the security and confidentiality of the models due to emerging vulnerabilities in prediction APIs. Of particular concern are model cloning attacks, where individuals with limited data and no knowledge of the training dataset manage to replicate a victim model's functionality …

apis arxiv confidentiality cs.cr data datasets deep learning defense deployment emerging extraction free led machine machine learning machine learning models model extraction security service services vulnerabilities