Artificial Neural Networks and Fault Injection Attacks
This work tackles security vulnerabilities in AI hardware for researchers and practitioners, but it appears incremental as it builds on known concepts from cryptography.
The chapter addresses the security of AI and neural network accelerators against fault injection attacks by comparing assets with cryptographic systems to define threat models, and explores fault attacks on these platforms.
This chapter is on the security assessment of artificial intelligence (AI) and neural network (NN) accelerators in the face of fault injection attacks. More specifically, it discusses the assets on these platforms and compares them with ones known and well-studied in the field of cryptographic systems. This is a crucial step that must be taken in order to define the threat models precisely. With respect to that, fault attacks mounted on NNs and AI accelerators are explored.