Stealthy and robust glitch injection attack on deep learning accelerator for target with variational viewpoint

• المؤلفون الرئيسيون: Liu, Wenye, Chang, Chip-Hong, Zhang, Fan
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2021
• الموضوعات: Engineering::Electrical and electronic engineering::Integrated circuits; Engineering::Electrical and electronic engineering::Computer hardware, software and systems; Artificial Intelligence; Deep Learning
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/146196
• المؤسسة: Nanyang Technological University

Deep neural network (DNN) accelerators overcome the power and memory walls for executing neural-net models locally on edge-computing devices to support sophisticated AI applications. The advocacy of 'model once, run optimized anywhere' paradigm introduces potential new security threat to e...