Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels

arXiv:2402.11953v1 Announce Type: cross
Abstract: Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily available to the public, is fine-tuned to suit specific tasks. As Machine Learning as a Service (MLaaS) platforms increasingly use pre-trained models in their backends, it's crucial to safeguard these architectures and understand their vulnerabilities. In this work, we present an approach …

abstract adversarial adversarial examples applications architecture arxiv become cnn cs.cr cs.lg domain examples integral machine machine learning practice public stealing systems through transfer transfer learning type