| 邹敏辉,周俊龙,孙晋,汪成亮.基于木马的方式增强RRAM计算系统的安全性.软件学报,2021,32(8):6-0 |
| 基于木马的方式增强RRAM计算系统的安全性 |
| Enhancing the Security of RRAM Computing System Based on Trojans |
| 投稿时间：2020-07-25 修订日期：2020-09-07 |
| DOI：10.13328/j.cnki.jos.006193 |
| 中文关键词: RRAM计算系统 木马 安全 |
| 英文关键词:RRAM computing system Trojan security |
| 基金项目:国家自然科学基金（61672115，61802185，61872185）；江苏省自然科学基金项目（BK20190447，BK20180470）；教育部中央高校基本科研业务费专项资金项目（30919011233，30919011402）；中国博士后科学基金资助项目（2020M680068） |
|
| 摘要点击次数: 74 |
| 全文下载次数: 40 |
| 中文摘要: |
| 基于新型存储器件RRAM的计算系统，因为能够在内存中执行矩阵点乘向量运算而受到广泛的关注.然而RRAM计算系统的安全性却未受到足够的重视.攻击者通过访问未授权的RRAM计算系统，进而以黑盒攻击的方式来获取存储于RRAM计算系统中的神经网络模型.本文的目标是阻止此种攻击.本文提出的防御方法是基于良性木马，也就是当RRAM计算系统未授权时，系统中的木马极容易被激活，进而影响系统的输出预测准确性，从而保证系统不能够正常运行；当RRAM计算系统被授权时，系统中的木马极难被误激活，从而系统能够正常运行.我们通过实验表明，该方法能够使得未授权的RRAM计算系统的输出预测准确性降低至15%以下，并且硬件开销小于系统中RRAM硬件的4.5%. |
| 英文摘要: |
| Computing systems based on the emerging device resistive random-access memory (RRAM) have received a lot of attention due to its cability of performing matrix-vector-multiplications operations in memory. However, the security of the RRAM computing system has not been paid enough attention. An attacker can gain access to the neural network models stored in the RRAM computing system by illegally accessing an unauthorized RRAM computing system and then carring on a black-box attack. The goal of this paper is to thwart such attacks. The defense method proposed in this paper is based on benign Trojan, which means that when the RRAM computing system is not authorized, the Trojan in the system are extremely easy to be activated, which in turn affects the prediction accuracy of the system's output, thus ensuring that the system is not able to operate normally; when the RRAM computing system is authorized, the Trojan in the system are extremely difficult to be activated accidently, thus enabling the system to operate normally. We show experimentally that the method enables the output prediction accuracy of an unauthorized RRAM computing system to be reduced to less than 20%, with a hardware overhead of less than 4.5% of the RRAM devices in the system. |
|
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
