scispace - formally typeset
Search or ask a question
Topic

Trojan

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


Papers
More filters
Journal ArticleDOI
Hassan Salmani1
TL;DR: Using an unsupervised clustering analysis, the paper shows that the controllability and observability characteristics of Trojan gates present significant inter-cluster distance from those of genuine gates in a Trojan-inserted circuit, such that Trojan gates are easily distinguishable.
Abstract: This paper presents a novel hardware Trojan detection technique in gate-level netlist based on the controllability and observability analyses. Using an unsupervised clustering analysis, the paper shows that the controllability and observability characteristics of Trojan gates present significant inter-cluster distance from those of genuine gates in a Trojan-inserted circuit, such that Trojan gates are easily distinguishable. The proposed technique does not require any golden model and can be easily integrated into the current integrated circuit design flow. Furthermore, it performs a static analysis and does not require any test pattern application for Trojan activation either partially or fully. In addition, the timing complexity of the proposed technique is an order of the number of signals in a circuit. Moreover, the proposed technique makes it possible to fully restore an inserted Trojan and to isolate its trigger and payload circuits. The technique has been applied on various types of Trojans, and all Trojans are successfully detected with 0 false positive and negative rates in less than 14 s in the worst case.

157 citations

Proceedings ArticleDOI
09 Jun 2008
TL;DR: This paper investigates a power supply transient signal analysis method for detecting Trojans that is based on the analysis of multiple power port signals and focuses on determining the smallest detectable Trojan in a set of process simulation models that characterize a TSMC 0.18 um process.
Abstract: Trust in reference to integrated circuits addresses the concern that the design and/or fabrication of the IC may be purposely altered by an adversary. The insertion of a hardware Trojan involves a deliberate and malicious change to an IC that adds or removes functionality or reduces its reliability. Trojans are designed to disable and/or destroy the IC at some future time or they may serve to leak confidential information covertly to the adversary. Trojans are cleverly hidden by the adversary to make it extremely difficult for chip validation processes, such as manufacturing test, to accidentally discover them. This paper investigates a power supply transient signal analysis method for detecting Trojans that is based on the analysis of multiple power port signals. In particular, we focus on determining the smallest detectable Trojan in a set of process simulation models that characterize a TSMC 0.18 um process.

157 citations

Posted Content
Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, Dawn Song 
TL;DR: TABOR formalizes a trojan detection task as a non-convex optimization problem, and the detection of a Trojan backdoor as the task of resolving the optimization through an objective function, and designs a new objective function that could guide optimization to identify aTrojan backdoor in a more effective fashion.
Abstract: A trojan backdoor is a hidden pattern typically implanted in a deep neural network. It could be activated and thus forces that infected model behaving abnormally only when an input data sample with a particular trigger present is fed to that model. As such, given a deep neural network model and clean input samples, it is very challenging to inspect and determine the existence of a trojan backdoor. Recently, researchers design and develop several pioneering solutions to address this acute problem. They demonstrate the proposed techniques have a great potential in trojan detection. However, we show that none of these existing techniques completely address the problem. On the one hand, they mostly work under an unrealistic assumption (e.g. assuming availability of the contaminated training database). On the other hand, the proposed techniques cannot accurately detect the existence of trojan backdoors, nor restore high-fidelity trojan backdoor images, especially when the triggers pertaining to the trojan vary in size, shape and position. In this work, we propose TABOR, a new trojan detection technique. Conceptually, it formalizes a trojan detection task as a non-convex optimization problem, and the detection of a trojan backdoor as the task of resolving the optimization through an objective function. Different from the existing technique also modeling trojan detection as an optimization problem, TABOR designs a new objective function--under the guidance of explainable AI techniques as well as heuristics--that could guide optimization to identify a trojan backdoor in a more effective fashion. In addition, TABOR defines a new metric to measure the quality of a trojan backdoor identified. Using an anomaly detection method, we show the new metric could better facilitate TABOR to identify intentionally injected triggers in an infected model and filter out false alarms......

154 citations

Journal ArticleDOI
TL;DR: In this article, the authors present 66 new near-infrared (NIR; 0.7-2.5m) spectra of 58 Trojan asteroids, including members of both the leading and trailing swarms.
Abstract: The Trojan asteroids, a very substantial population of primitive bodies trapped in Jupiter's stable Lagrange regions, remain quite poorly understood. Because they occupy these orbits, the physical properties of Trojans provide a unique perspective on the chemical and dynamical processes that shaped the Solar System. The current study was therefore undertaken to investigate surface compositions of these objects. We present 66 new near-infrared (NIR; 0.7-2.5??m) spectra of 58 Trojan asteroids, including members of both the leading and trailing swarms. We also include in the analysis previously published NIR spectra of 13 Trojans (3 of which overlap with the new sample). This data set permits not only a direct search for compositional signatures, but also a search for patterns that may reveal clues to the origin of the Trojans. We do not report any confirmed absorption features in the new spectra. Analysis of the spectral slopes, however, reveals an interesting bimodality among the NIR data. The two spectral groups identified appear to be equally abundant in the leading and trailing swarms. The spectral groups are not a result of family membership; they occur in the background, non-family population. The average albedos of the two groups are the same within uncertainties (0.051 ? 0.016 and 0.055 ? 0.016). No correlations between spectral slope and any other physical or orbital parameter are detected, with the exception of a possible weak correlation with inclination among the less-red spectral group. The NIR spectral groups are consistent with a similar bimodality previously suggested among visible colors and spectra. Synthesizing the present results with previously published properties of Trojans, we conclude that the two spectral groups represent objects with different intrinsic compositions. We further suggest that whereas the less-red group originated near Jupiter or in the main asteroid belt, the redder spectral group originated farther out in the Solar System. If this suggestion is correct, the Trojan swarms offer the most readily accessible large reservoir of Kuiper Belt material as well as a unique reservoir for the study of material from the middle part of the solar nebula.

153 citations

Proceedings ArticleDOI
27 Jul 2009
TL;DR: This paper analyzes time to generate a transition in functional Trojans and fully activate them and proposes an efficient dummy flip-flop insertion procedure that can significantly increase Trojan activity and reduce Trojan activation time.
Abstract: Hardware Trojans in integrated circuits and systems have become serious concern to fabless semiconductor industry and government agencies in recent years. Most of the previously proposed Trojan detection methods rely on Trojan activation to either observe a faulty output or measure side-channel signals such as transient current or charge. From the authentication stand point, time to trigger a hardware Trojan circuit is a a major concern. This paper analyzes time to (i) generate a transition in functional Trojans and (ii) fully activate them. An efficient dummy flip-flop insertion procedure is proposed to increase Trojan activity. Depending on authentication time and circuit topology, a transition probability threshold is selected so that inserted dummy flip-flops would moderately impact area overhead. The simulation results on s38417 benchmark circuit demonstrate that, with a negligible area overhead, our proposed method can significantly increase Trojan activity and reduce Trojan activation time.

150 citations


Network Information
Related Topics (5)
Cloud computing
156.4K papers, 1.9M citations
70% related
Cache
59.1K papers, 976.6K citations
70% related
Planet
27K papers, 980.6K citations
68% related
Compiler
26.3K papers, 578.5K citations
66% related
Key (cryptography)
60.1K papers, 659.3K citations
66% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023136
2022282
2021111
2020139
2019144
2018168