Arithmetic Masking Countermeasure to Mitigate Side-Channel-Based Model Extraction Attack on DNN Accelerator
- 23 October 2025
- book chapter
- Published by Springer Nature
- p. 94-112
Abstract
No abstract availableKeywords
This publication has 20 references indexed in Scilit:
- LoS Trick: Countermeasure against CPA for DNN Models Using Loss of Significance in Multiply-Accumulate Operations2024
- NNLeak: An AI-Oriented DNN Model Extraction Attack through Multi-Stage Side Channel Analysis2023
- MERCURY: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator2023
- On (in)Security of Edge-based Machine Learning Against Electromagnetic Side-channels2022
- Shuffling Countermeasure against Power Side-Channel Attack for MLP with Software Implementation2021
- Remote Power Attacks on the Versatile Tensor Accelerator in Multi-Tenant FPGAs2021
- DeepEM: Deep Neural Networks Model Recovery through EM Side-Channel Information Leakage2020
- Model Reverse-Engineering Attack using Correlation Power Analysis against Systolic Array Based Neural Network Accelerator2020
- Model-Extraction Attack Against FPGA-DNN Accelerator Utilizing Correlation Electromagnetic Analysis2019
- Correlation Power Analysis with a Leakage Model2004