{"title":"A Reconfigurable High-Speed ECC Processor Over NIST Primes","authors":"Jinnan Ding, Shuguo Li","doi":"10.1109/Trustcom/BigDataSE/ICESS.2017.353","DOIUrl":null,"url":null,"abstract":"Elliptic curve cryptography (ECC) is widely used in the field of cyber security such as TLS protocol. Compared with symmetric cryptography, the computation of ECC is much slower. In this paper, a reconfigurable high-speed processor supporting all currently used NIST primes on FPGA platform is constructed. The modular addition and substraction is eliminated in our design by applying lazy reduction strategy. Throughput of modular multiplication is improved significantly with Karatsuba algorithm and compact pipeline schedule. The latency of modular inverse is tactfully avoided by pipeline coverage at the level of scalar multiplication. Furthermore, Montgomery-ladder algorithm and base-point randomization is applied to resist side-channel and timing attacks. Most of these techniques can also be used in software designs. Compared with previous works, our FPGA design outperforms times of others in term of scalar multiplication performance, while the hardware cost remains moderate, which makes it suitable for computation-intensive applications.","PeriodicalId":170253,"journal":{"name":"2017 IEEE Trustcom/BigDataSE/ICESS","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Trustcom/BigDataSE/ICESS","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/Trustcom/BigDataSE/ICESS.2017.353","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9
Abstract
Elliptic curve cryptography (ECC) is widely used in the field of cyber security such as TLS protocol. Compared with symmetric cryptography, the computation of ECC is much slower. In this paper, a reconfigurable high-speed processor supporting all currently used NIST primes on FPGA platform is constructed. The modular addition and substraction is eliminated in our design by applying lazy reduction strategy. Throughput of modular multiplication is improved significantly with Karatsuba algorithm and compact pipeline schedule. The latency of modular inverse is tactfully avoided by pipeline coverage at the level of scalar multiplication. Furthermore, Montgomery-ladder algorithm and base-point randomization is applied to resist side-channel and timing attacks. Most of these techniques can also be used in software designs. Compared with previous works, our FPGA design outperforms times of others in term of scalar multiplication performance, while the hardware cost remains moderate, which makes it suitable for computation-intensive applications.