On (in)security of edge-based machine learning against electromagnetic side-channels

• Main Authors: Bhasin, Shivam, Jap, Dirmanto, Picek, Stjepan
• Other Authors: 2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI)
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Electrical and electronic engineering::Computer hardware, software and systems; Side-Channel Analysis; Machine Learning
• Online Access: https://hdl.handle.net/10356/165224
• Institution: Nanyang Technological University

Machine (deep) learning represents mainstream re- search and development direction. This success can be linked to the ever-increasing computational capabilities and vast amounts of available data, resulting in ever more sophisticated machine learning models. The design and training of such machine l...