Filters: Keyword is Integrated circuit modeling  [Clear All Filters]
MATSUNAGA, Y., AOKI, N., DOBASHI, Y., KOJIMA, T..  2020.  A Black Box Modeling Technique for Distortion Stomp Boxes Using LSTM Neural Networks. 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). :653–656.
This paper describes an experimental result of modeling stomp boxes of the distortion effect based on a machine learning approach. Our proposed technique models a distortion stomp box as a neural network consisting of LSTM layers. In this approach, the neural network is employed for learning the nonlinear behavior of the distortion stomp boxes. All the parameters for replicating the distortion sound are estimated through its training process using the input and output signals obtained from some commercial stomp boxes. The experimental result indicates that the proposed technique may have a certain appropriateness to replicate the distortion sound by using the well-trained neural networks.
Lin, T., Shi, Y., Shu, N., Cheng, D., Hong, X., Song, J., Gwee, B. H..  2020.  Deep Learning-Based Image Analysis Framework for Hardware Assurance of Digital Integrated Circuits. 2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA). :1—6.
We propose an Artificial Intelligence (AI)/Deep Learning (DL)-based image analysis framework for hardware assurance of digital integrated circuits (ICs). Our aim is to examine and verify various hardware information from analyzing the Scanning Electron Microscope (SEM) images of an IC. In our proposed framework, we apply DL-based methods at all essential steps of the analysis. To the best of our knowledge, this is the first such framework that makes heavy use of DL-based methods at all essential analysis steps. Further, to reduce time and effort required in model re-training, we propose and demonstrate various automated or semi-automated training data preparation methods and demonstrate the effectiveness of using synthetic data to train a model. By applying our proposed framework to analyzing a set of SEM images of a large digital IC, we prove its efficacy. Our DL-based methods are fast, accurate, robust against noise, and can automate tasks that were previously performed mainly manually. Overall, we show that DL-based methods can largely increase the level of automation in hardware assurance of digital ICs and improve its accuracy.
Larasati, H. T., Kim, H..  2020.  Simulation of Modular Exponentiation Circuit for Shor's Algorithm in Qiskit. 2020 14th International Conference on Telecommunication Systems, Services, and Applications (TSSA. :1–7.
This paper discusses and demonstrates the construction of a quantum modular exponentiation circuit in the Qiskit simulator for use in Shor's Algorithm for integer factorization problem (IFP), which is deemed to be able to crack RSA cryptosystems when a large-qubit quantum computer exists. We base our implementation on Vedral, Barenco, and Ekert (VBE) proposal of quantum modular exponentiation, one of the firsts to explicitly provide the aforementioned circuit. Furthermore, we present an example simulation of how to construct a 7xmod 15 circuit in a step-by-step manner, giving clear and detailed information and consideration that currently not provided in the existing literature, and present the whole circuit for use in Shor's Algorithm. Our present simulation shows that the 4-bit VBE quantum modular exponentiation circuit can be constructed, simulated, and measured in Qiskit, while the Shor's Algorithm incorporating this VBE approach itself can be constructed but not yet simulated due to an overly large number of QASM instructions.
Alabugin, S. K., Sokolov, A. N..  2020.  Applying of Generative Adversarial Networks for Anomaly Detection in Industrial Control Systems. 2020 Global Smart Industry Conference (GloSIC). :199–203.

Modern industrial control systems (ICS) act as victims of cyber attacks more often in last years. These cyber attacks often can not be detected by classical information security methods. Moreover, the consequences of cyber attack's impact can be catastrophic. Since cyber attacks leads to appearance of anomalies in the ICS and technological equipment controlled by it, the task of intrusion detection for ICS can be reformulated as the task of industrial process anomaly detection. This paper considers the applicability of generative adversarial networks (GANs) in the field of industrial processes anomaly detection. Existing approaches for GANs usage in the field of information security (such as anomaly detection in network traffic) were described. It is proposed to use the BiGAN architecture in order to detect anomalies in the industrial processes. The proposed approach has been tested on Secure Water Treatment Dataset (SWaT). The obtained results indicate the prospects of using the examined method in practice.

Gillen, R. E., Anderson, L. A., Craig, C., Johnson, J., Columbia, A., Anderson, R., Craig, A., Scott, S. L..  2020.  Design and Implementation of Full-Scale Industrial Control System Test Bed for Assessing Cyber-Security Defenses. 2020 IEEE 21st International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM). :341—346.
In response to the increasing awareness of the Ethernet-based threat surface of industrial control systems (ICS), both the research and commercial communities are responding with ICS-specific security solutions. Unfortunately, many of the properties of ICS environments that contribute to the extent of this threat surface (e.g. age of devices, inability or unwillingness to patch, criticality of the system) similarly prevent the proper testing and evaluation of these security solutions. Production environments are often too fragile to introduce unvetted technology and most organizations lack test environments that are sufficiently consistent with production to yield actionable results. Cost and space requirements prevent the creation of mirrored physical environments leading many to look towards simulation or virtualization. Examples in literature provide various approaches to building ICS test beds, though most of these suffer from a lack of realism due to contrived scenarios, synthetic data and other compromises. In this paper, we provide a design methodology for building highly realistic ICS test beds for validating cybersecurity defenses. We then apply that methodology to the design and building of a specific test bed and describe the results and experimental use cases.
Tai, J., Alsmadi, I., Zhang, Y., Qiao, F..  2020.  Machine Learning Methods for Anomaly Detection in Industrial Control Systems. 2020 IEEE International Conference on Big Data (Big Data). :2333—2339.

This paper examines multiple machine learning models to find the model that best indicates anomalous activity in an industrial control system that is under a software-based attack. The researched machine learning models are Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Recurrent Neural Network classifiers built-in Python and tested against the HIL-based Augmented ICS dataset. Although the results showed that Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Long Short-Term Memory classification models have great potential for anomaly detection in industrial control systems, we found that Random Forest with tuned hyperparameters slightly outperformed the other models.

Wang, F., Zhang, X..  2020.  Secure Resource Allocation for Polarization-Based Non-Linear Energy Harvesting Over 5G Cooperative Cognitive Radio Networks. ICC 2020 - 2020 IEEE International Conference on Communications (ICC). :1–6.
We address secure resource allocation for the energy harvesting (EH) based 5G cooperative cognitive radio networks (CRNs). To guarantee that the size-limited secondary users (SUs) can simultaneously send the primary user's and their own information, we assume that SUs are equipped with orthogonally dual-polarized antennas (ODPAs). In particular, we propose, develop, and analyze an efficient resource allocation scheme under a practical non-linear EH model, which can capture the nonlinear characteristics of the end-to-end wireless power transfer (WPT) for radio frequency (RF) based EH circuits. Our obtained numerical results validate that a substantial performance gain can be obtained by employing the non-linear EH model.
Li, M., Wang, F., Gupta, S..  2020.  Data-driven fault model development for superconducting logic. 2020 IEEE International Test Conference (ITC). :1—5.

Superconducting technology is being seriously explored for certain applications. We propose a new clean-slate method to derive fault models from large numbers of simulation results. For this technology, our method identifies completely new fault models – overflow, pulse-escape, and pattern-sensitive – in addition to the well-known stuck-at faults.

Chau, Cuong, Hunt, Warren A., Kaufmann, Matt, Roncken, Marly, Sutherland, Ivan.  2019.  A Hierarchical Approach to Self-Timed Circuit Verification. 2019 25th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC). :105–113.
Self-timed circuits can be modeled in a link-joint style using a formally defined hardware description language. It has previously been shown how functional properties of these models can be formally verified with the ACL2 theorem prover using a scalable, hierarchical method. Here we extend that method to parameterized circuit families that may have loops and non-deterministic outputs. We illustrate this extension with iterative self-timed circuits that calculate the greatest common divisor of two natural numbers, with circuits that perform arbitrated merges non-deterministically, and with circuits that combine both of these.
Eneh, Joy Nnenna, Onyekachi Orah, Harris, Emeka, Aka Benneth.  2019.  Improving the Reliability and Security of Active Distribution Networks Using SCADA Systems. 2019 IEEE PES/IAS PowerAfrica. :110–115.
The traditional electricity distribution system is rapidly shifting from the passive infrastructure to a more active infrastructure, giving rise to a smart grid. In this project an active electricity distribution network and its components have been studied. A 14-node SCADA-based active distribution network model has been proposed for managing this emerging network infrastructure to ensure reliability and protection of the network The proposed model was developed using matlab /simulink software and the fuzzy logic toolbox. Surge arresters and circuit breakers were modelled and deployed in the network at different locations for protection and isolation of fault conditions. From the reliability analysis of the proposed model, the failure rate and outage hours were reduced due to better response of the system to power fluctuations and fault conditions.
Das, Debayan, Nath, Mayukh, Chatterjee, Baibhab, Ghosh, Santosh, Sen, Shreyas.  2019.  S℡LAR: A Generic EM Side-Channel Attack Protection through Ground-Up Root-Cause Analysis. 2019 IEEE International Symposium on Hardware Oriented Security and Trust (HOST). :11–20.
The threat of side-channels is becoming increasingly prominent for resource-constrained internet-connected devices. While numerous power side-channel countermeasures have been proposed, a promising approach to protect the non-invasive electromagnetic side-channel attacks has been relatively scarce. Today's availability of high-resolution electromagnetic (EM) probes mandates the need for a low-overhead solution to protect EM side-channel analysis (SCA) attacks. This work, for the first time, performs a white-box analysis to root-cause the origin of the EM leakage from an integrated circuit. System-level EM simulations with Intel 32 nm CMOS technology interconnect stack, as an example, reveals that the EM leakage from metals above layer 8 can be detected by an external non-invasive attacker with the commercially available state-of-the-art EM probes. Equipped with this `white-box' understanding, this work proposes S℡LAR: Signature aTtenuation Embedded CRYPTO with Low-Level metAl Routing, which is a two-stage solution to eliminate the critical signal radiation from the higher-level metal layers. Firstly, we propose routing the entire cryptographic core within the local lower-level metal layers, whose leakage cannot be picked up by an external attacker. Then, the entire crypto IP is embedded within a Signature Attenuation Hardware (SAH) which in turn suppresses the critical encryption signature before it routes the current signature to the highly radiating top-level metal layers. System-level implementation of the S℡LAR hardware with local lower-level metal routing in TSMC 65 nm CMOS technology, with an AES-128 encryption engine (as an example cryptographic block) operating at 40 MHz, shows that the system remains secure against EM SCA attack even after 1M encryptions, with 67% energy efficiency and 1.23× area overhead compared to the unprotected AES.
Daoud, Luka, Rafla, Nader.  2019.  Analysis of Black Hole Router Attack in Network-on-Chip. 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS). :69–72.

Network-on-Chip (NoC) is the communication platform of the data among the processing cores in Multiprocessors System-on-Chip (MPSoC). NoC has become a target to security attacks and by outsourcing design, it can be infected with a malicious Hardware Trojan (HT) to degrades the system performance or leaves a back door for sensitive information leaking. In this paper, we proposed a HT model that applies a denial of service attack by deliberately discarding the data packets that are passing through the infected node creating a black hole in the NoC. It is known as Black Hole Router (BHR) attack. We studied the effect of the BHR attack on the NoC. The power and area overhead of the BHR are analyzed. We studied the effect of the locations of BHRs and their distribution in the network as well. The malicious nodes has very small area and power overhead, 1.98% and 0.74% respectively, with a very strong violent attack.

Liu, Y., Li, L., Gao, Q., Cao, J., Wang, R., Sun, Z..  2019.  Analytical Model of Torque-Prediction for a Novel Hybrid Rotor Permanent Magnet Machines. IEEE Access. 7:109528–109538.

This paper presents an analytical method for predicting the electromagnetic performance in permanent magnet (PM) machine with the spoke-type rotor (STR) and a proposed hybrid rotor structure (HRS), respectively. The key of this method is to combine magnetic field analysis model (MFAM) with the magnetic equivalent circuit model. The influence of the irregular PM shape is considered by the segmentation calculation. To obtain the boundary condition in the MFAM, respectively, two equivalent methods on the rotor side are proposed. In the STR, the average flux density of the rotor core outer-surface is calculated to solve the Laplace's equation with considering for the rotor core outer-surface eccentric. In the HRS, based on the Thevenin's theorem, the equivalent parameters of PM remanence BreB and thickness hpme are obtained as a given condition, which can be utilized to compute the air-gap flux density by conventional classic magnetic field analysis model of surface-mounted PMs with air-gap region. Finally, the proposed analytical models are verified by the finite element analysis (FEA) with comparisons of the air-gap flux density, flux linkage, back-EMF and electromagnetic torque, respectively. Furthermore, the performance that the machine with the proposed hybrid structure rotor can improve the torque density as explained.

Nozaki, Yusuke, Yoshikawa, Masaya.  2019.  Countermeasure of Lightweight Physical Unclonable Function Against Side-Channel Attack. 2019 Cybersecurity and Cyberforensics Conference (CCC). :30–34.

In industrial internet of things, various devices are connected to external internet. For the connected devices, the authentication is very important in the viewpoint of security; therefore, physical unclonable functions (PUFs) have attracted attention as authentication techniques. On the other hand, the risk of modeling attacks on PUFs, which clone the function of PUFs mathematically, is pointed out. Therefore, a resistant-PUF such as a lightweight PUF has been proposed. However, new analytical methods (side-channel attacks: SCAs), which use side-channel information such as power or electromagnetic waves, have been proposed. The countermeasure method has also been proposed; however, an evaluation using actual devices has not been studied. Since PUFs use small production variations, the implementation evaluation is very important. Therefore, this study proposes a SCA countermeasure of the lightweight PUF. The proposed method is based on the previous studies, and maintains power consumption consistency during the generation of response. In experiments using a field programmable gate array, the measured power consumption was constant regardless of output values of the PUF could be confirmed. Then, experimental results showed that the predicted rate of the response was about 50 %, and the proposed method had a tamper resistance against SCAs.

Balijabudda, Venkata Sreekanth, Thapar, Dhruv, Santikellur, Pranesh, Chakraborty, Rajat Subhra, Chakrabarti, Indrajit.  2019.  Design of a Chaotic Oscillator based Model Building Attack Resistant Arbiter PUF. 2019 Asian Hardware Oriented Security and Trust Symposium (AsianHOST). :1—6.

Physical Unclonable Functions (PUFs) are vulnerable to various modelling attacks. The chaotic behaviour of oscillating systems can be leveraged to improve their security against these attacks. We have integrated an Arbiter PUF implemented on a FPGA with Chua's oscillator circuit to obtain robust final responses. These responses are tested against conventional Machine Learning and Deep Learning attacks for verifying security of the design. It has been found that such a design is robust with prediction accuracy of nearly 50%. Moreover, the quality of the PUF architecture is evaluated for uniformity and uniqueness metrics and Monte Carlo analysis at varying temperatures is performed for determining reliability.

Fujdiak, Radek, Blazek, Petr, Mlynek, Petr, Misurec, Jiri.  2019.  Developing Battery of Vulnerability Tests for Industrial Control Systems. 2019 10th IFIP International Conference on New Technologies, Mobility and Security (NTMS). :1–5.

Nowadays, the industrial control systems (ICS) face many challenges, where security is becoming one of the most crucial. This fact is caused by new connected environment, which brings among new possibilities also new vulnerabilities, threats, or possible attacks. The criminal acts in the ICS area increased over the past years exponentially, which caused the loss of billions of dollars. This also caused classical Intrusion Detection Systems and Intrusion Prevention Systems to evolve in order to protect among IT also ICS networks. However, these systems need sufficient data such as traffic logs, protocol information, attack patterns, anomaly behavior marks and many others. To provide such data, the requirements for the test environment are summarized in this paper. Moreover, we also introduce more than twenty common vulnerabilities across the ICS together with information about possible risk, attack vector (point), possible detection methods and communication layer occurrence. Therefore, the paper might be used as a base-ground for building sufficient data generator for machine learning and artificial intelligence algorithms often used in ICS/IDS systems.

Han, Tao, Wang, Yuze, Liu, Peng.  2019.  Hardware Trojans Detection at Register Transfer Level Based on Machine Learning. 2019 IEEE International Symposium on Circuits and Systems (ISCAS). :1–5.

To accurately detect Hardware Trojans in integrated circuits design process, a machine-learning-based detection method at the register transfer level (RTL) is proposed. In this method, circuit features are extracted from the RTL source codes and a training database is built using circuits in a Hardware Trojans library. The training database is used to train an efficient detection model based on the gradient boosting algorithm. In order to expand the Hardware Trojans library for detecting new types of Hardware Trojans and update the detection model in time, a server-client mechanism is used. The proposed method can achieve 100% true positive rate and 89% true negative rate, on average, based on the benchmark from Trust-Hub.

Gay, Maël, Paxian, Tobias, Upadhyaya, Devanshi, Becker, Bernd, Polian, Ilia.  2019.  Hardware-Oriented Algebraic Fault Attack Framework with Multiple Fault Injection Support. 2019 Workshop on Fault Diagnosis and Tolerance in Cryptography (FDTC). :25–32.

The evaluation of fault attacks on security-critical hardware implementations of cryptographic primitives is an important concern. In such regards, we have created a framework for automated construction of fault attacks on hardware realization of ciphers. The framework can be used to quickly evaluate any cipher implementations, including any optimisations. It takes the circuit description of the cipher and the fault model as input. The output of the framework is a set of algebraic equations, such as conjunctive normal form (CNF) clauses, which is then fed to a SAT solver. We consider both attacking an actual implementation of a cipher on an field-programmable gate array (FPGA) platform using a fault injector and the evaluation of an early design of the cipher using idealized fault models. We report the successful application of our hardware-oriented framework to a collection of ciphers, including the advanced encryption standard (AES), and the lightweight block ciphers LED and PRESENT. The corresponding results and a discussion of the impact to different fault models on our framework are shown. Moreover, we report significant improvements compared to similar frameworks, such as speedups or more advanced features. Our framework is the first algebraic fault attack (AFA) tool to evaluate the state-of-the art cipher LED-64, PRESENT and full-scale AES using only hardware-oriented structural cipher descriptions.

Danger, Jean-Luc, Fribourg, Laurent, Kühne, Ulrich, Naceur, Maha.  2019.  LAOCOÖN: A Run-Time Monitoring and Verification Approach for Hardware Trojan Detection. 2019 22nd Euromicro Conference on Digital System Design (DSD). :269–276.

Hardware Trojan Horses and active fault attacks are a threat to the safety and security of electronic systems. By such manipulations, an attacker can extract sensitive information or disturb the functionality of a device. Therefore, several protections against malicious inclusions have been devised in recent years. A prominent technique to detect abnormal behavior in the field is run-time verification. It relies on dedicated monitoring circuits and on verification rules generated from a set of temporal properties. An important question when dealing with such protections is the effectiveness of the protection against unknown attacks. In this paper, we present a methodology based on automatic generation of monitoring and formal verification techniques that can be used to validate and analyze the quality of a set of temporal properties when used as protection against generic attackers of variable strengths.

Guo, Xiaolong, Zhu, Huifeng, Jin, Yier, Zhang, Xuan.  2019.  When Capacitors Attack: Formal Method Driven Design and Detection of Charge-Domain Trojans. 2019 Design, Automation Test in Europe Conference Exhibition (DATE). :1727–1732.

The rapid growth and globalization of the integrated circuit (IC) industry put the threat of hardware Trojans (HTs) front and center among all security concerns in the IC supply chain. Current Trojan detection approaches always assume HTs are composed of digital circuits. However, recent demonstrations of analog attacks, such as A2 and Rowhammer, invalidate the digital assumption in previous HT detection or testing methods. At the system level, attackers can utilize the analog properties of the underlying circuits such as charge-sharing and capacitive coupling effects to create information leakage paths. These new capacitor-based vulnerabilities are rarely covered in digital testings. To address these stealthy yet harmful threats, we identify a large class of such capacitor-enabled attacks and define them as charge-domain Trojans. We are able to abstract the detailed charge-domain models for these Trojans and expose the circuit-level properties that critically contribute to their information leakage paths. Aided by the abstract models, an information flow tracking (IFT) based solution is developed to detect charge-domain leakage paths and then identify the charge-domain Trojans/vulnerabilities. Our proposed method is validated on an experimental RISC microcontroller design injected with different variants of charge-domain Trojans. We demonstrate that successful detection can be accomplished with an automatic tool which realizes the IFT-based solution.

Serpanos, Dimitrios, Stachoulis, Dimitrios.  2019.  Secure Memory for Embedded Tamper-Proof Systems. 2019 14th International Conference on Design Technology of Integrated Systems In Nanoscale Era (DTIS). :1–4.

Data leakage and disclosure to attackers is a significant problem in embedded systems, considering the ability of attackers to get physical access to the systems. We present methods to protect memory data leakage in tamper-proof embedded systems. We present methods that exploit memory supply voltage manipulation to change the memory contents, leading to an operational and reusable memory or to destroy memory cell circuitry. For the case of memory data change, we present scenaria for data change to a known state and to a random state. The data change scenaria are effective against attackers who cannot detect the existence of the protection circuitry; furthermore, original data can be calculated in the case of data change to a known state, if the attacker identifies the protection circuitry and its operation. The methods that change memory contents to a random state or destroy memory cell circuitry lead to irreversible loss of the original data. However, since the known state can be used to calculate the original data.

Islam, S. A., Sah, L. K., Katkoori, S..  2019.  DLockout: A Design Lockout Technique for Key Obfuscated RTL IP Designs. 2019 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS). :17–20.
Intellectual Property (IP) infringement including piracy and overproduction have emerged as significant threats in the semiconductor supply chain. Key-based obfuscation techniques (i.e., logic locking) are widely applied to secure legacy IP from such attacks. However, the fundamental question remains open whether an attacker is allowed an exponential amount of time to seek correct key or could it be useful to lock out the design in a non-destructive manner after several incorrect attempts. In this paper, we address this question with a robust design lockout technique. Specifically, we perform comparisons on obfuscation logic output that reflects the condition (correct or incorrect) of the applied key without changing the system behavior. The proposed approach, when combined with key obfuscation (logic locking) technique, increases the difficulty of reverse engineering key obfuscated RTL module. We provide security evaluation of DLockout against three common side-channel attacks followed by a quantitative assessment of the resilience. We conducted a set of experiments on four datapath intensive IPs and one crypto core for three different key lengths (32-, 64-, and 128-bit) under the typical design corner. On average, DLockout incurs negligible area, power, and delay overheads.
Hong, Junho, Nuqui, Reynaldo F., Kondabathini, Anil, Ishchenko, Dmitry, Martin, Aaron.  2019.  Cyber Attack Resilient Distance Protection and Circuit Breaker Control for Digital Substations. IEEE Transactions on Industrial Informatics. 15:4332—4341.
This paper proposes new concepts for detecting and mitigating cyber attacks on substation automation systems by domain-based cyber-physical security solutions. The proposed methods form the basis of a distributed security domain layer that enables protection devices to collaboratively defend against cyber attacks at substations. The methods utilize protection coordination principles to cross check protection setting changes and can run real-time power system analysis to evaluate the impact of the control commands. The transient fault signature (TFS)-based cross-correlation coefficient algorithm has been proposed to detect the false sampled values data injection attack. The proposed functions were verified in a hardware-in-the-loop (HIL) simulation using commercial relays and a real-time digital simulator (RTDS). Various types of cyber intrusions are tested using this test bed to evaluate the consequences and impacts of cyber attacks to power grid as well as to validate the performance of the proposed research-grade cyber attack mitigation functions.
Noeren, Jannis, Parspour, Nejila.  2019.  A Dynamic Model for Contactless Energy Transfer Systems. 2019 IEEE PELS Workshop on Emerging Technologies: Wireless Power Transfer (WoW). :297—301.

Inductive contactless energy transfer (CET) systems show a certain oscillating transient behavior of inrush currents on both system sides. This causes current overshoots in the electrical components and has to be considered for the system dimensioning. This paper presents a simple and yet very accurate model, which describes the dynamic behavior of series-series compensated inductive CET systems. This model precisely qualifies the systems current courses for both sides in time domain. Additionally, an analysis in frequency domain allows further knowledge for parameter estimation. Since this model is applicable for purely resistive loads and constant voltage loads with bridge rectifiers, it is very practicable and can be useful for control techniques and narameter estimation.

Wang, Yuze, Han, Tao, Han, Xiaoxia, Liu, Peng.  2019.  Ensemble-Learning-Based Hardware Trojans Detection Method by Detecting the Trigger Nets. 2019 IEEE International Symposium on Circuits and Systems (ISCAS). :1–5.

With the globalization of integrated circuit (IC) design and manufacturing, malicious third-party vendors can easily insert hardware Trojans into their intellect property (IP) cores during IC design phase, threatening the security of IC systems. It is strongly required to develop hardware-Trojan detection methods especially for the IC design phase. As the particularity of Trigger nets in Trojan circuits, in this paper, we propose an ensemble-learning-based hardware-Trojan detection method by detecting the Trigger nets at the gate level. We extract the Trigger-net features for each net from known netlists and use the ensemble learning method to train two detection models according to the Trojan types. The detection models are used to identify suspicious Trigger nets in an unknown detected netlist and give results of suspiciousness values for each detected net. By flagging the top n% suspicious nets of each detection model as the suspicious Trigger nets based on the suspiciousness values, the proposed method can achieve, on average, 88% true positive rate, 90% true negative rate, and 90% Accuracy.