近年来，硬件安全性越来越突出，这是由于全球化的半导体供应链和第三方IP（知识产权）使用的增加而引起的担忧。木马检测对于确保系统的机密性、完整性和可用性至关重要。现有的FPGA（现场可编程门阵列）硬件木马检测方法包括测试时方法、预实现方法和运行时方法。前两种方法提供了检测某些特洛伊木马的有效方法;然而，特洛伊木马可能被专门设计为在测试时或实现之前避免检测，从而使运行时检测成为更有吸引力的选择。运行时检测和删除特洛伊木马程序是非常可取的，由于广泛的关键系统部署在FPGA上，可能很难或昂贵的从操作中删除。硬件和自然系统之间有许多相似之处，其中一个例子在硬件攻击和生物攻击之间建立了类比。我们提出了一种受CRISPR-Cas启发的（聚类规则间隔回文重复序列）方法，用于检测FPGA中的硬件木马。1-E型CRISPR-Cas机制的基本概念被讨论和模拟，以预测遗传信息通过该生物系统的流动。利用该系统的基本结构，提出了一种新型的运行时木马检测方法CADEFT（CRISPR-Cas-based Algorithm for Detection of FPGA Trojans）。探讨了FPGA不同层次的应用设计流程，提出了在比特流级实现CADEFT，以监控FPGA的配置比特流和运行时特性。CADEFT的灵活性源于CRISPR-Cas机制识别可能对系统构成威胁的类似模式的能力。
英文摘要：
Hardware security has risen in prominence in recent years with concerns stemming from a globalizing semiconductor supply chain and increased third-party IP (intellectual property) usage. Trojan detection is of paramount importance for ensuring systems with confidentiality, integrity, and availability. Existing methods for hardware Trojan detection in FPGA (field programmable gate array) devices include test-time methods, pre-implementation methods, and run-time methods. The first two methods provide effective ways of detecting some Trojans; however, Trojans may be specifically designed to avoid detection at test-time or before implementation making run-time detection a more attractive option. Run-time detection and removal of Trojans is highly desirable due to the wide range of critical systems which are deployed on FPGAs and may be difficult or costly to remove from operation. Many parallels can be drawn between hardware and natural systems, and one example creates an analogy between hardware attacks and biological attacks. We propose a CRISPR-Cas-inspired (clustered regularly interspaced palindromic repeats) method for detecting hardware Trojans in FPGAs. The fundamental concepts of the Type 1-E CRISPR-Cas mechanism are discussed and simulated to predict the flow of genetic information through this biological system. The basic structure of this system is utilized to propose a novel run-time Trojan detection method titled CADEFT (CRISPR-Cas-based Algorithm for DEtection of FPGA Trojans). Different levels of FPGA application design flow are explored, and CADEFT is proposed for realization at the bitstream level to monitor the configuration bitstream and the run-time properties of the FPGA. The flexibility of CADEFT originates in the CRISPR-Cas mechanism's ability to recognize similar albeit previously unseen patterns which may pose a threat to the system.
FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
Zhejiang University（浙江大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Chinese Aeronautical Establishment（中国航空研究院）；National University of Defense Technology（国防科技大学）
Technische Universität Wien (TU Wien)（维也纳工业大学）；Tennessee Tech. University（田纳西理工大学）；National University of Sciences and Technology (NUST)（国立科技大学）；United Arab Emirates University（阿联酋大学）；New York University Abu Dhabi (NYU AD)（纽约大学阿布扎比分校）
