.png){kind=icon}
返回
Secure Machine Learning Hardware: Challenges and Progress
.png){kind=icon}
PRE
AI
DOI：10.1109/MCAS.2024.3509376.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the rising adoption of deep neural networks (DNNs) for commercial and high-stakes applications that process sensitive user data and make critical decisions, security concerns are paramount. An adversary can undermine the confidentiality of user input or a DNN model, mislead a DNN to make wrong predictions, or even render a machine learning application unavailable to valid requests. While security vulnerabilities that enable such exploits can exist across multiple levels of the technology stack that supports machine learning applications, the hardware-level vulnerabilities can be particularly problematic. In this article, we provide a comprehensive review of the hardware-level vulnerabilities affecting domain-specific DNN inference accelerators and recent progress in secure hardware design to address these. As domain-specific DNN accelerators have a number of differences compared to general-purpose processors and cryptographic accelerators where the hardware-level vulnerabilities have been thoroughly investigated, there are unique challenges and opportunities for secure machine learning hardware. We first categorize the hardware-level vulnerabilities into three scenarios based on an adversary's capability: 1) an adversary can only attack the off-chip components, such as the off-chip DRAM and the data bus; 2) an adversary can directly attack the on-chip structures in a DNN accelerator; and 3) an adversary can insert hardware trojans during the manufacturing and design process. For each category, we survey recent studies on attacks that pose practical security challenges to DNN accelerators. Then, we present recent advances in the defense solutions for DNN accelerators, addressing those security challenges with circuit-, architecture-, and algorithm-level techniques.
Keyword:
Surveys
Program processors
Reviews
Random access memory
Artificial neural networks
Machine learning
Predictive models
System-on-chip
Security
Trojan horses
Domain specific languages
Hardware security
DNN accelerators
sidechannel attacks
fault injection attacks
memory security
hardware trojan
期刊
IF:
3.5
论文数:
530
被引数:
1.3K
机构
引用论文
The synthesis, structures and reactions of zinc and cobalt metal–organic frameworks incorporating an alkyne-based dicarboxylate linker.png)
CrystEngComm
OAAI
CrystEngCommIF0
OAAI分享收藏Effects of local cholinesterase inhibition on acetylcholine release assessed simultaneously in prefrontal and frontoparietal cortexNeuroscience
NeuroscienceIF0
PREAI
分享收藏INTRASPECIFIC RESERVOIRS: COMPLEX LIFE HISTORY AND THE PERSISTENCE OF A LETHAL RANAVIRUSEcology
EcologyIF0
PREAI
分享收藏
查看更多内容