arrow
返回

Sample augmentation-based adversarial training method to counter evasive spectre attacks

delete2025-12-29
delete0
PRE
AI
Z
Zhongkai Tong *
J
Jian Gao
D
Deyu Yuan
刘
刘刚 (Gang Liu)
DOI:10.1016/j.engappai.2025.113634delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• 一种新型的规避Spectre攻击绕过了基于AI的高性能计算(HPC)检测系统。 • 基于样本扩展的对抗性训练可以检测规避Spectre攻击。 • 结合硬件事件将所需的对抗样本数量最多减少了94%。

期刊

Engineering Applications of Artificial Intelligence 封面图
Engineering Applications of Artificial Intelligence
IF:
8
论文数:
5.7K
被引数:
3.5W

机构

C
China Telecom Research Institute
学者数:
50
论文数: 17
被引数: 0
P
People’s Public Security University of China
学者数:
18
论文数: 8
被引数: 0
引用论文

引用论文

Spectre Attacks: Exploiting Speculative Execution
err2020-06-18
err98
PREAI
errKocher, Paul; Horn, Jann; Fogh, Anders; Genkin, Daniel; Gruss, Daniel; Haas, Werner; Hamburg, Mike; Lipp, Moritz; Mangard, Stefan; Prescher, Thomas; Schwarz, Michael; Yarom, Yuval
err分享
err收藏
Adversarial Attack on Microarchitectural Events based Malware Detectors
err2019-06-02
err0
PREAI
errSai Manoj Pudukotai Dinakarrao; Sairaj Amberkar; Sahil Bhat; Abhijitt Dhavlle; Hossein Sayadi; Avesta Sasan; Houman Homayoun; Setareh Rafatirad
err分享
err收藏
学者 查看更多内容