Trojan

About: Trojan is a research topic. Over the lifetime, 2028 publications have been published within this topic receiving 33209 citations.

Hardware Trojan Detection Through Chip-Free Electromagnetic Side-Channel Statistical Analysis

Abstract: The hardware Trojan (HT) has become a major threat for the integrated circuit (IC) industry and supply chain, and has motivated numerous developments of Trojan detection schemes. Although the side-channel method is the most promising one, nearly all of the side-channel methods require fabricated golden chips, which are very difficult to obtain in reality. In this paper, we propose a novel strategy for HT detection using electromagnetic side-channel-based spectrum modeling and analyzing. We utilize the design data at early stage of the IC lifecycle, and the generated spectrum can serve as the golden reference, and thus we do not need the fabricated golden chips anymore. Another very important feature is that our method is immune to the process variation theoretically. Experimental results on selected Advanced Encryption Standard benchmark circuits on FPGA show that our proposed method can effectively detect Trojans even with very small traces.

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

Abstract: 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.

The resonant structure of Jupiter's Trojan asteroids – I. Long‐term stability and diffusion

Abstract: We study the global dynamics of the jovian Trojan asteroids by means of the frequency map analysis. We find and classify the main resonant structures that serve as skeleton of the phase space near the Lagrangian points. These resonances organize and control the long-term dynamics of the Trojans. Besides the secondary and secular resonances, that have already been found in other asteroid sets in mean motion resonance (e.g. main belt, Kuiper belt), we identify a new type of resonance that involves secular frequencies and the frequency of the great inequality, but not the libration frequency. Moreover, this new family of resonances plays an important role in the slow transport mechanism that drives Trojans from the inner stable region to eventual ejections. Finally, we relate this global view of the dynamics with the observed Trojans, identify the asteroids that are close to these resonances and study their long-term behaviour.

Composite Backdoor Attack for Deep Neural Network by Mixing Existing Benign Features

Abstract: With the prevalent use of Deep Neural Networks (DNNs) in many applications, security of these networks is of importance. Pre-trained DNNs may contain backdoors that are injected through poisoned training. These trojaned models perform well when regular inputs are provided, but misclassify to a target output label when the input is stamped with a unique pattern called trojan trigger. Recently various backdoor detection and mitigation systems for DNN based AI applications have been proposed. However, many of them are limited to trojan attacks that require a specific patch trigger. In this paper, we introduce composite attack, a more flexible and stealthy trojan attack that eludes backdoor scanners using trojan triggers composed from existing benign features of multiple labels. We show that a neural network with a composed backdoor can achieve accuracy comparable to its original version on benign data and misclassifies when the composite trigger is present in the input. Our experiments on 7 different tasks show that this attack poses a severe threat. We evaluate our attack with two state-of-the-art backdoor scanners. The results show none of the injected backdoors can be detected by either scanner. We also study in details why the scanners are not effective. In the end, we discuss the essence of our attack and propose possible defense.