Hardware Trojan Detection Using Deep Learning-Deep Stacked Auto Encoder

Vishnupriya, R.; M, Nirmala Devi

doi:10.1007/978-981-15-7234-0_30

Cited by 8 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the utilized features are the same as [5]. Similarly, [10] adopted an auto-encoder model for HT detection, but the features are still manually designed based on the prior knowledge of the circuits. Although [11] attempted to auto-encode the circuit structures as features, their proposed encoding method has to still use pre-knowledge of the netlist transition probability and the detection accuracy still highly depends on the manual adjustment of parameters.…”

Section: Previous Researchmentioning

confidence: 99%

“…For example, machine learning (ML)-based and neural network (NN)based HT detection methods have been proposed to detect and prevent HT-insertion at design-time without involving any extra complicated pre-processing or introducing additional overheads. In these approaches, HT related features are directly extracted from circuit designs and fed into ML/NN models to train HT detection models [4], [5], [6], [7], [8], [9], [10], [11]. Existing ML/NN-based HT detection methods have to depend on the pre-understanding of the characteristics of a circuit netlist (called knowledge-driven) to extract effective features for training ML/NN models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Hardware Trojan Detection With Block-Based Netlist Information Extraction

Liu

et al. 2022

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

With the globalization of the semiconductor industry, hardware Trojans (HTs) are an emergent security threat in modern integrated circuit (IC) production. Research is now being conducted into designing more accurate and efficient methods to detect HTs. Recently, a number of machine learning (ML)-based HT detection approaches have been proposed; however, most of them still use knowledge-driven approaches to design features and often use engineering intuition to carefully craft the detection model to improve accuracy. Therefore, in this work, we propose a data-driven HT detection system based on gate-level netlists. The system consists of four main parts: 1) Information extraction from netlist block; 2) Natural language processing (NLP) for translating netlist information; 3) Deel learning (DL)-based HT detection model; 4) HT component final voter. In the experiments, both a long short-term memory networks (LSTM) model and convolutional neural network (CNN) model are used as our detection models. We performed the experiments on the HT benchmarks from Trust-hub and K-fold crossing verification has been applied to evaluate different parameter settings in the training procedure. The experimental results show that the proposed HT detection system can achieve 79.29% TPR, 99.97% TNR, 87.75% PPV and 99.94% NPV for combinational Trojan detection and 93.46% TPR, 99.99% TNR, 98.92% PPV and 99.92% NPV for sequential Trojan detection after voting-based optimization using the LEDA library-based HT benchmarks (logic level=4, upsampling, LSTM, 5 epochs).

show abstract

Section: Previous Researchmentioning

confidence: 99%