摘要
在大数据和人工智能时代,全同态加密方法被公认为是解决数据安全与隐私泄露问题的理想技术,但目前存在计算效率差、密文膨胀等问题,严重影响了全同态加密技术的应用和推广。从针对全同态加密算法的硬件加速和围绕全同态加密算法的优化2个方面,回顾了2023年计算机体系结构与密码学相关研究进展:以专用集成电路技术路线为代表的硬件加速效果明显;从算法角度进行优化,进展显著。可以预测,未来几年内,同态加密将与人工智能技术相结合,在跨行业、行业总分机构数据协作和利用中发挥更多价值。
In the era of big data and artificial intelligence,homomorphic encryption methods are widely recognized as an ideal technology to solve data security and privacy leakage problems.However,there are currently issues such as poor computational efficiency and ciphertext inflation,which seriously affect application and promotion of this technology.On the basis of summarizing the current research status,this paper reviews and analyzes the relevant research progress in 2023 from two aspects:hardware acceleration for homomorphic encryption algorithms and optimization of homomorphic encryption algorithms.Significant acceleration effects are attributed to the dedicated integrated circuit technology route;substantial progress has been made in optimization from the algorithm perspective.It can be predicted that in the next few years homomorphic encryption will be combined with artificial intelligence to deliver more value in cross-industry and industry division data collaboration and utilization.
作者
范瑞琦
陈铭志
牛鑫丽
董文阔
李晓霖
刘硕
刘静
赵明
蔡嘉跃
闫闱
朱树永
郑珂威
徐鹏
郝沁汾
孙凝晖
FAN Ruiqi;CHEN Mingzhi;NIU Xinli;DONG Wenkuo;LI Xiaolin;LIU Shuo;LIU Jing;ZHAO Ming;CAI Jiayue;YAN Wei;ZHU Shuyong;ZHENG Kewei;XU Peng;HAO Qinfen;SUN Ninghui(Institute of Computing Technology,Chinese Academy of Science,Beijing 100086,China;Wuxi Xingguangtongtai LTD.,Wuxi 214104,China;Wuxi Institute of Integrate Chip and Interconnect Technology,Wuxi 214104,China;School of Cyber Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China)
出处
《科技导报》
CAS
CSCD
北大核心
2024年第1期286-295,共10页
Science & Technology Review
关键词
全同态加密
数据安全
隐私泄露防护
计算机体系结构
密码学
fully homomorphic encryption
data security
privacy leakage protection
computer architecture
cryptography