Exploiting device-level non-idealities for adversarial attacks on ReRAM-based neural networks

Exploiting device-level non-idealities for adversarial attacks on ReRAM-based neural networks

Resistive memory (ReRAM) or memristor devices offer the prospect of more efficient computing. While memristors have been used for a variety of computing systems, their usage has gained significant popularity in the domain of deep learning. Weight matrices in deep neural networks can be mapped to cro...

Full description

Bibliographic Details
Main Authors: Tyler McLemore, Robert Sunbury, Seth Brodzik, Zachary Cronin, Elias Timmons, Dwaipayan Chakraborty
Format: Article
Language:English
Published: Elsevier 2023-07-01
Series:Memories - Materials, Devices, Circuits and Systems
Subjects:
ReRAM
Memristor
Non-ideality
Neural network
Adversarial attack
Explainable AI
Online Access:http://www.sciencedirect.com/science/article/pii/S2773064623000300

Internet

http://www.sciencedirect.com/science/article/pii/S2773064623000300

Similar Items