2 papers
cs.CR2025
Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
Ashley Kurian, Aydin Aysu
Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protec…
cs.CR2025
No TPU Left Behind: Retrofitting Side-Channel Protection into Edge TPUs
Ashley Kurian, Anuj Dubey, Modini Ayyagari +1
Side-channel attacks can recover neural network parameters from physical signals, even on commercial edge accelerators. Existing defenses require changes to hardware, instruction s…