DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories-Reference-Cited by-同舟云学术

DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories

Author:

Rakin Adnan Siraj¹,Chowdhuryy Md Hafizul Islam²,Yao Fan²,Fan Deliang¹

Affiliation:

1. Arizona State University,School of Electrical, Computer, and Energy Engineering,Tempe,AZ

2. University of Central Florida,Department of Electrical and Computer Engineering,Orlando,FL

Funder

National Science Foundation

Publisher

IEEE

Link

Reference89 articles.

2. Theoretically principled trade-off between robustness and accuracy;zhang;International Conference on Machine Learning,2019

Cited by 33 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Read Disturbance in High Bandwidth Memory: A Detailed Experimental Study on HBM2 DRAM Chips;2024 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN);2024-06-24

2. An Experimental Characterization of Combined RowHammer and RowPress Read Disturbance in Modern DRAM Chips;2024 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S);2024-06-24

3. Owl: Differential-Based Side-Channel Leakage Detection for CUDA Applications;2024 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN);2024-06-24