AI Attacks AI: Recovering Neural Network architecture from NVDLA using AI-assisted Side Channel Attack

ePrint Report: AI Attacks AI: Recovering Neural Network architecture from NVDLA using AI-assisted Side Channel Attack

Naina Gupta, Arpan Jati, Anupam Chattopadhyay

During the last decade, there has been a stunning progress in the domain of AI with adoption in both safety-critical and security-critical applications. A key requirement for this is highly trained Machine Learning (ML) models, which are valuable Intellectual Property (IP) of the respective organizations. Naturally, these models have become targets for model recovery attacks through side-channel leakage. …

adoption applications architecture attack attacks channel critical domain eprint report intellectual property key machine machine learning network neural network progress report safety safety-critical security