USENIX Security '24 - SoK: All You Need to Know About On-Device ML Model Extraction - The Gap... скачать в хорошем качестве

USENIX Security '24 - SoK: All You Need to Know About On-Device ML Model Extraction - The Gap...

SoK: All You Need to Know About On-Device ML Model Extraction - The Gap Between Research and Practice Tushar Nayan, Qiming Guo, and Mohammed Al Duniawi, Florida International University; Marcus Botacin, Texas A&M University; Selcuk Uluagac and Ruimin Sun, Florida International University On-device ML is increasingly used in different applications. It brings convenience to offline tasks and avoids sending user-private data through the network. On-device ML models are valuable and may suffer from model extraction attacks from different categories. Existing studies lack a deep understanding of on-device ML model security, which creates a gap between research and practice. This paper provides a systematization approach to classify existing model extraction attacks and defenses based on different threat models. We evaluated well known research projects from existing work with real-world ML models, and discussed their reproducibility, computation complexity, and power consumption. We identified the challenges for research projects in wide adoption in practice. We also provided directions for future research in ML model extraction security. View the full USENIX Security '24 program at https://www.usenix.org/conference/use...