ModelShield: A Generic and Portable Framework Extension for Defending Bit-Flip based Adversarial Weight Attacks
2021 IEEE 39th International Conference on Computer Design (ICCD)(2021)
摘要
Bit-flip attack (BFA) has become one of the most serious threats to Deep Neural Network (DNN) security. By utilizing Rowhammer to flip the bits of DNN weights stored in memory, the attacker can turn a functional DNN into a random output generator. In this work, we propose ModelShield, a defense mechanism against BFA, based on protecting the integrity of weights using hash verification. ModelShield...
更多查看译文
关键词
Deep learning,Computational modeling,Conferences,Software,Real-time systems,Generators,Computer security
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要