首页> 外文会议>IEEE International Symposium on Nanoelectronic and Information Systems >Secure Information Processing during System-Level: Exploration of an Optimized Trojan Secured Datapath for CDFGs during HLS Based on User Constraints
【24h】

Secure Information Processing during System-Level: Exploration of an Optimized Trojan Secured Datapath for CDFGs during HLS Based on User Constraints

机译:系统级的安全信息处理:基于用户约束的HLS期间CDFG的优化木马安全数据路径的探索

获取原文

摘要

Globalization of the System-on-Chip (SoC) design process poses a serious security alarm for SoC integrators, due to involvement of untrustworthy third party (3P) vendors supplying intellectual property (IP) cores. In this paper, a novel methodology for design space exploration in high level synthesis (HLS) is presented for loop based control data flow graphs (CDFG), which provides secure information processing against hardware Trojan in 3PIPs. The proposed approach performs this system level protection by exploration of an optimized combination of Trojan secured dual modular redundant (DMR) datapath and loop unrolling factor (U) by employing a novel particle swarm encoding scheme. Further, the approach also presents a novel technique for efficient exploration of vendor allocation procedure for hardware capable of Trojan detection. Finally, the approach presents a novel area-delay tradeoff during exploration of Trojan secured datapath and unrolling factor. Results indicated an average improvement in Quality of Results (QoR) of ~12% compared to a similar prior research.
机译:由于不值得信任的第三方(3P)供应商提供知识产权(IP)核心,芯片上芯片(SOC)设计过程的全球化对SoC集成商的严重安全报警构成了SoC Integrators。本文介绍了高级合成(HLS)设计空间探索的新型方法,用于循环的控制数据流图(CDFG),其为3PIPS中的硬件特洛伊木马提供安全信息处理。通过采用新颖的粒子群编码方案,所提出的方法通过探讨特洛伊木马安全双模冗余(DMR)DataPath和循环展开因子(U)的优化组合来执行该系统级别保护。此外,该方法还提出了一种新颖的技术,可用于有效探索能够进行特洛伊木马检测的硬件的供应商分配程序。最后,该方法在探索木马担保数据路径和展开因子期间提出了一种新的区域延迟权衡。结果表明,与类似的先前研究相比,〜12%的结果(QOR)的平均改善。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号