首页 | 本学科首页   官方微博 | 高级检索  
     

面向嵌入式系统的加密算法性能检测方法
引用本文:柯亚文,蔡挺,夏晓峰,向宏. 面向嵌入式系统的加密算法性能检测方法[J]. 重庆大学学报(自然科学版), 2020, 43(11): 1-10
作者姓名:柯亚文  蔡挺  夏晓峰  向宏
作者单位:重庆大学 大数据与软件学院, 重庆 400044;重庆大学 信息物理社会可信服务计算教育部重点实验室, 重庆 400044
基金项目:国家重点研发计划资助项目(2017YFB0802400);"十三五"国家密码发展基金资助项目(MMJJ20180211);重庆市研究生导师团队建设项目(ydstd1821)。
摘    要:嵌入式系统信息安全是保障工业控制系统安全的必然要求,然而有限成本的硬件资源可能无法有效支撑加密算法应用所带来的额外计算开销。为研究面向嵌入式系统中加密算法移植的可行性和对系统性能的影响,提出了一个嵌入式系统加密算法性能度量方法,通过构建等效度量实现系统侧和密码侧两部分抽象层次的联系。实验利用该方法,以运行时间延迟、吞吐量和系统资源使用率为度量指标,完成对包括国产加密算法与轻量级算法等在内的多种不同配置加密算法的性能测评。实验结果表明加密算法密钥长度的增长会增加算法执行的延时,算法分组大小的增大会提高算法的运行速度,使用不同加密模式造成的性能影响随加密算法不同而表现出差异性。直接部署加密算法检测任务执行时系统的指标值可以简化测量,相比其他抽象模型在工业场景中的应用更有实际意义。

关 键 词:嵌入式系统  加密算法  性能检测  轻量级密码  Xilinx ZYNQ
收稿时间:2020-07-11

Methods of encryption algorithm performance detection oriented to embedded system
KE Yawen,CAI Ting,XIA Xiaofeng,XIANG Hong. Methods of encryption algorithm performance detection oriented to embedded system[J]. Journal of Chongqing University(Natural Science Edition), 2020, 43(11): 1-10
Authors:KE Yawen  CAI Ting  XIA Xiaofeng  XIANG Hong
Affiliation:School of Bigdata and Software Engineering, Ministry of Education, Chongqing 400044, P. R. China;Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing 400044, P. R. China
Abstract:Embedded system security is an inevitable requirement for ensuring the security of industrial control systems. However, the cost-limited hardware resources may not be able to effectively support the additional calculation overhead brought by the application of encryption algorithms. In this paper, we focusd on the feasibility of the migration of encryption algorithms for embedded systems and the impact on the system performance. And a performance benchmark method of encryption algorithm for embedded system was proposed to realize the connection between the system side and the cipher side by constructing equivalent metrics. The experiment carried out by this method covered the performance benchmark of encryption algorithms with different configurations including domestic encryption algorithm and lightweight cryptography algorithm with running time delay, throughput and system resource utilization as metrics. The experimental results show that the increase in the encryption algorithm key length will increase the algorithm execution delay, and the increase in the algorithm packet size will accelerate the algorithm''s running speed. The performance impact caused by the use of different encryption modes will vary with the encryption algorithm. Direct deployment of encryption algorithm to detect system index values during task execution can simplify the measurement and is more practical than the application of other abstract models in industrial scene.
Keywords:embedded systems  encryption algorithm  performance benchmark  lightweight cryptography  Xilinx ZYNQ
点击此处可从《重庆大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《重庆大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号