GPU Overdrive Fault Attacks on Neural Networks

2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)(2021)

引用 1|浏览13
暂无评分
摘要
Graphics processing units (GPUs) are commonly used to accelerate training and inference of deep neural networks (DNNs). Modern cloud nodes are shared by multiple users to execute workloads concurrently. However, the reliability and security of sharing the heterogeneous CPU-GPU have not been carefully evaluated. In this paper, we thoroughly characterize fault injections and propagation in a victim ...
更多
查看译文
关键词
Training,Deep learning,Design automation,Neural networks,Graphics processing units,Controllability,Timing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要