Improving the accuracy and robustness of RRAM-based in-memory computing against RRAM hardware noise and adversarial attacks. (13th January 2022)

• Record Type: Journal Article
• Authors: Kiran Cherupally, Sai; Meng, Jian; Siraj Rakin, Adnan; Yin, Shihui; Yeo, Injune; Yu, Shimeng; Fan, Deliang; Seo, Jae-Sun
• Is Part Of: Semiconductor science and technology. Volume 37:Number 3(2022)
• Publication Date: 2022-01-13
• Subjects: IMC noise-aware training -- RRAM-friendly DNNs -- Adversarial defense with RRAM noise; Semiconductors -- Periodicals; 621.38152
• DOI: 10.1088/1361-6641/ac461f
• Languages: English
• ISSNs: 0268-1242

Abstract

Abstract: We present a novel deep neural network (DNN) training scheme and resistive RAM (RRAM) in-memory computing (IMC) hardware evaluation towards achieving high accuracy against RRAM device/array variations and enhanced robustness against adversarial input attacks. We present improved IMC inference accuracy results evaluated on state-of-the-art DNNs including ResNet-18, AlexNet, and VGG with binary, 2-bit, and 4-bit activation/weight precision for the CIFAR-10 dataset. These DNNs are evaluated with measured noise data obtained from three different RRAM-based IMC prototype chips. Across these various DNNs and IMC chip measurements, we show that our proposed hardware noise-aware DNN training consistently improves DNN inference accuracy for actual IMC hardware, up to 8% accuracy improvement for the CIFAR-10 dataset. We also analyze the impact of our proposed noise injection scheme on the adversarial robustness of ResNet-18 DNNs with 1-bit, 2-bit, and 4-bit activation/weight precision. Our results show up to 6% improvement in the robustness to black-box adversarial input attacks.