.png){kind=icon}
返回
Enabling Secure NVM-Based in-Memory Neural Network Computing by Sparse Fast Gradient Encryption
.png){kind=icon}
PRE
AI
DOI：10.1109/TC.2020.3017870.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural network (NN) computing is energy-consuming on traditional computing systems, owing to the inherent memory wall bottleneck of the von Neumann architecture and the Moore's Law being approaching the end. Non-volatile memories (NVMs) have been demonstrated as promising alternatives for constructing computing-in-memory (CIM) systems to accelerate NN computing. However, NVM-based NN computing systems are vulnerable to the confidentiality attacks because the weight parameters persist in memory when the system is powered off, enabling an adversary with physical access to extract the well-trained NN models. The goal of this article is to find a solution for thwarting the confidentiality attacks. We define and model the weight encryption problem. Then we propose an effective framework, containing a sparse fast gradient encryption (SFGE) method and a runtime encryption scheduling (RES) scheme, to guarantee the confidentiality security of NN models with a negligible performance overhead. Moreover, we improve the SFGE method by incrementally generating the encryption keys. Additionally, we provide variants of the encryption method to better fit quantized models and various mapping strategies. The experiments demonstrate that only encrypting an extremely small proportion of the weights (e.g., 20 weights per layer in ResNet-101), the NN models can be strictly protected.
Keyword:
Artificial neural networks
Nonvolatile memory
Encryption
Computational modeling
Hardware
Non-volatile memory (NVM)
compute-in-memory (CIM)
neural network
security
encryption
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.8
论文数:
5.4K
被引数:
9.8K
机构
引用论文
分享收藏Reliability and Validity of the Novaco Anger Scale and Provocation Inventory (NAS-PI) and State-Trait Anger Expression Inventory-2 (STAXI-2) in Hispanic and Non-Hispanic White Student SamplesNovaco愤怒量表和挑衅量表 (nas-pi) 和状态特质愤怒表达量表-2 (STAXI-2) 在西班牙裔和非西班牙裔白人学生样本中的可靠性和有效性
PREAI
分享收藏Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey计算机视觉中对抗性攻击对深度学习的威胁: 一项调查.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容