Physical security of deep learning on edge devices : comprehensive evaluation of fault injection attack vectors

• المؤلفون الرئيسيون: Hou, Xiaolu, Breier, Jakub, Jap, Dirmanto, Ma, Lei, Bhasin, Shivam, Liu, Yang
• مؤلفون آخرون: Temasek Laboratories @ NTU
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Computer science and engineering::Hardware::Performance and reliability; Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Fault Attack; Neural Network
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/156095

Decision making tasks carried out by the usage of deep neural networks are successfully taking over in many areas, including those that are security critical, such as healthcare, transportation, smart grids, where intentional and unintentional failures can be disastrous. Edge computing systems are b...