A deep learning based malicious module identification using stacked sparse autoencoder network for VLSI circuit reliability

•A deep learning- based hardware trojan identification method is proposed.•The data imbalance in VLSI circuits is addressed by using deep convolutional generative adversarial network.•More suitable features are extracted using handcrafted algorithms and structural reports.•Stacked autoencoder and st...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Measurement : journal of the International Measurement Confederation Ročník 194; s. 111055
Hlavní autoři: Priyatharishini, M., Nirmala Devi, M.
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Elsevier Ltd 15.05.2022
Elsevier Science Ltd
Témata:
Circuit design
Circuit reliability
Deep learning
Feature
Feature extraction
Generative Adversarial Network
Hardware Trojan
Identification methods
Integrated circuits
Learning
Modules
Network reliability
Neural networks
Optimization
Performance degradation
Sparsity
Stacked Sparse Autoencoder
Threat models
Very large scale integration
Generative Adversarial Network
Feature
Hardware Trojan
Stacked Sparse Autoencoder
ISSN:0263-2241, 1873-412X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A deep learning- based hardware trojan identification method is proposed.•The data imbalance in VLSI circuits is addressed by using deep convolutional generative adversarial network.•More suitable features are extracted using handcrafted algorithms and structural reports.•Stacked autoencoder and stacked sparse autoencoder model is used to discover the malicious logic in the gate level netlist.•The significance of sparsity is achieved by stacked sparse autoencoder technique, which minimizes the detection probability. The rate of development of technology and its associated security issues are increasing in integrated circuit industry. This provides a space for implanting dormant nature of threats, named Hardware Trojan (HT) in various process of integrated circuits (IC) design. The impact of HT’s emanates the encrypted signals, privacy disruption, performance degradation or denial of service. The threat models are unimaginable and it can be intruded at any stage which complicates the HT detection process. Therefore, a deep learning-based malicious module identification method is proposed in this work by implementing stacked autoencoder and stacked sparse autoencoder model. The simulation results shows that the proposed stacked sparse autoencoder outperforms the best in detecting the malicious modifications with an average accuracy of 97.53%, true positive rate of 93% and moreover the true negative rate achieved is 98.14% which proves the effectiveness of sparsity nature in extracting suitable features in the proposed schemes.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2022.111055