The computer systems security arms race between attackers and defenders are largely taken place in the domain of software systems, but as hardware complexity and design processes have envolved, novel and potent hardware-based security threats are now possible. This article presents Unused Circuit Identification (UCI), an approach for detecting suspicious circuits during design time, and BlueChip, a hybrid hardware/software approach to detaching suspicious circuits and making up for UCI classifier errors during runtime.

Overcoming an untrusted computing base: detecting and removing malicious hardware automatically

Recently, due to the increase of outsourcing in IC design, it has been reported that malicious third-party vendors often insert hardware Trojans into their ICs. How to detect them is a strong concern in IC design process. The features of hardware-Trojan infected nets (or Trojan nets) in ICs often differ from those of normal nets. To classify all the nets in netlists designed by third-party vendors into Trojan ones and normal ones, we have to extract effective Trojan features from Trojan nets. In this paper, we first propose 51 Trojan features which describe Trojan nets from netlists. Based on the importance values obtained from the random forest classifier, we extract the best set of 11 Trojan features out of the 51 features which can effectively detect Trojan nets, maximizing the F-measures. By using the 11 Trojan features extracted, the machine-learning based hardware Trojan classifier has achieved at most 100% true positive rate as well as 100% true negative rate in several TrustHUB benchmarks and obtained the average F-measure of 74.6%, which realizes the best values among existing machine-learning-based hardware-Trojan detection methods.

Trojan-feature extraction at gate-level netlists and its application to hardware-Trojan detection using random forest classifier

The remarkable success of machine learning (ML) in a variety of research domains has inspired academic and industrial communities to explore its potential to address hardware Trojan (HT) attacks. While numerous works have been published over the past decade, few survey papers, to the best of our knowledge, have systematically reviewed the achievements and analyzed the remaining challenges in this area. To fill this gap, this article surveys ML-based approaches against HT attacks available in the literature. In particular, we first provide a classification of all possible HT attacks and then review recent developments from four perspectives, i.e., HT detection, design-for-security (DFS), bus security, and secure architecture. Based on the review, we further discuss the lessons learned in and challenges arising from previous studies. Despite current work focusing more on chip-layer HT problems, it is notable that novel HT threats are constantly emerging and have evolved beyond chips and to the component, device, and even behavior layers, therein compromising the security and trustworthiness of the overall hardware ecosystem. Therefore, we divide the HT threats into four layers and propose a hardware Trojan defense (HTD) reference model from the perspective of the overall hardware ecosystem, therein categorizing the security threats and requirements in each layer to provide a guideline for future research in this direction.

/pdf/a-survey-on-machine-learning-against-hardware-trojan-attacks-1awuivoz8l.pdf

A Survey on Machine Learning Against Hardware Trojan Attacks: Recent Advances and Challenges

Recently, due to the increase of outsourcing in IC design and manufacturing, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, it is strongly required to detect hardware Trojans because malicious third-party vendors can easily insert hardware Trojans in their products. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. We obtained at most 100% true positive rate with our proposed method.

Hardware Trojans classification for gate-level netlists using multi-layer neural networks

Malicious hardware modification, also known as hardware Trojan attack, has emerged as a serious security concern for electronic systems. Such attacks compromise the basic premise of hardware root of trust. Over the past decade, significant research efforts have been directed to carefully analyze the trust issues arising from hardware Trojans and to protect against them. This vast body of work often needs to rely on well-defined set of trust benchmarks that can reliably evaluate the effectiveness of the protection methods. In recent past, efforts have been made to develop a benchmark suite to analyze the effectiveness of pre-silicon Trojan detection and prevention methodologies. However, there are only a limited number of Trojan inserted benchmarks available. Moreover, there is an inherent bias as the researcher is aware of Trojan properties such as location and trigger condition since the current benchmarks are static. In order to create an unbiased and robust benchmark suite to evaluate the effectiveness of any protection technique, we have developed a comprehensive framework of automatic hardware Trojan insertion. Given a netlist, the framework will automatically generate a design with single or multiple Trojan instances based user-specified Trojan properties. It allows a wide variety of configurations, such as the type of Trojan, Trojan activation probability, number of triggers, and choice of payload. The tool ensures that the inserted Trojan is a valid one and allow for provisions to optimize the Trojan footprint (area and switching). Experiments demonstrate that a state-of-the-art Trojan detection technique provides poor efficacy when using benchmarks generated by our tool. This tool is available for download from http://www.trust-hub.org/.

An automated configurable Trojan insertion framework for dynamic trust benchmarks

Recently, we face a serious risk that malicious third-party vendors can very easily insert hardware Trojans into their IC products but it is very difficult to analyze huge and complex ICs. In this paper, we propose a hardware-Trojan classification method to identify hardware-Trojan infected nets (or Trojan nets) using a support vector machine (SVM). Firstly, we extract the five hardware-Trojan features in each net in a netlist. Secondly, since we cannot effectively give the simple and fixed threshold values to them to detect hardware Trojans, we represent them to be a five-dimensional vector and learn them by using SVM. Finally, we can successfully classify a set of all the nets in an unknown netlist into Trojan ones and normal ones based on the learned SVM classifier. We have applied our SVM-based hardware-Trojan classification method to Trust-HUB benchmarks and the results demonstrate that our method can much increase the true positive rate compared to the existing state-of-the-art results in most of the cases. In some cases, our method can achieve the true positive rate of 100%, which shows that all the Trojan nets in a netlist are completely detected by our method.

Hardware Trojans classification for gate-level netlists based on machine learning

A hardware-trojan classification method using machine learning at gate-level netlists based on Trojan features

Since hardware production become inexpensive and international, hardware vendors often outsource their products to third-party vendors. Due to the situation, malicious vendors can easily insert malfunctions (also known as “hardware Trojans”) to their products. In this paper, we experimentally evaluate a machine-learning-based hardware-Trojan detection method using several hardware Trojans we designed. To begin with, we design three types of hardware Trojans and insert them to simple RS232 transceiver circuits. After that, we learn known netlists, where we know which nets are Trojan ones or normal ones beforehand, using a machine-learning-based hardware-Trojan detection method with a support vector machine (SVM) classifier. Finally, we classify the nets in the designed hardware-Trojan-inserted netlists into a set of Trojan nets and that of normal nets using the learned classifier. The experimental results demonstrate that the hardware-Trojan detection method with the SVM-based approach can detect a part of hardware Trojans we designed.

Masao Yanagisawa

Papers

Trojan-feature extraction at gate-level netlists and its application to hardware-Trojan detection using random forest classifier

Hardware Trojans classification for gate-level netlists based on machine learning

Hardware Trojans classification for gate-level netlists using multi-layer neural networks

A hardware-trojan classification method using machine learning at gate-level netlists based on Trojan features

Designing hardware trojans and their detection based on a SVM-based approach