Knowledge Graph Embedding and Visualization for Pre-Silicon Detection of Hardware Trojans

Utyamishev, Dmitry; Partin-Vaisband, Inna

doi:10.1109/iscas48785.2022.9937418

Cited by 2 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphs are powerful representations where complex systems can be represented using nodes and edges. Recent advancements in GNNs have opened promising research directions allowing efficient learning of predictive representations from graph data ( 88 – 90 ), and contributing to the widespread interest in GNN among AI researchers and application domain experts ( 91 , 92 ). Graph-based representations have emerged as a new trend in computational drug development and discovery ( 93 , 94 ).…”

Section: Representations Of Drug Compoundsmentioning

confidence: 99%

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Partin

Brettin²,

Zhu³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

show abstract

Section: Representations Of Drug Compoundsmentioning

confidence: 99%

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Partin

Brettin²,

Zhu³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Policies that address all the metrics, as listed in Table I, are proposed. The concept of KGE for HT detection was first introduced in our recent work [23]. However, the model in [23] only supports a reduction in the search space for existing thirdparty HT detection tools.…”

Section: Proposed Frameworkmentioning

confidence: 99%

“…The concept of KGE for HT detection was first introduced in our recent work [23]. However, the model in [23] only supports a reduction in the search space for existing thirdparty HT detection tools. The high false-positive prediction rate prevents the model in [23] from being used as a standalone HT detection tool.…”

Section: Proposed Frameworkmentioning

confidence: 99%

“…However, the model in [23] only supports a reduction in the search space for existing thirdparty HT detection tools. The high false-positive prediction rate prevents the model in [23] from being used as a standalone HT detection tool. The approach proposed in this paper is based on two-stage semi-supervised classification.…”

Section: Proposed Frameworkmentioning

confidence: 99%

“…The correctness of the proposed embedding has been visually evaluated in our recent work [23], exhibiting a cluster of rarely triggered nets embedded in the center of the latent space. While significantly reducing the HT detection search space, the method in [23] exhibits low precision values, and, therefore, cannot be used to identify HTs without auxiliary HT detection tools. In this work, a KGE-complementary HT detection method is developed based on spatial characteristics of the embedded IC vectors.…”

Section: Proposed Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Netwise Detection of Hardware Trojans Using Scalable Convolution of Graph Embedding Clouds

Utyamishev,

Partin-Vaisband

2024

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Hardware Trojans (HTs) are malicious circuits that can be inserted into integrated circuits (ICs) during the design, manufacturing, or packaging phases. HTs can cause a variety of security and safety problems, such as data theft, denialof-service attacks, and physical damage. A scalable referencefree framework is introduced in this paper for netwise gatelevel detection of existing and unknown HTs. The proposed framework consists of embedding-based automated netlist graph analysis and a supervised convolution-based classification of the individual IC net embeddings. A novel convolution algorithm for learning embedded IC graphs has been developed to overcome fundamental scalability limitation of existing graph convolutional neural networks. The performance of the proposed framework is experimentally demonstrated based on the TrustHub TRIT-TC benchmark suite, yielding a high recall of 96% and a precision of 86% for the netwise detection. The individual HT-compromised nets are highlighted within less than 0.1 seconds in >17, 000gate ICs. The proposed framework provides a scalable way to detect existing and unknown HTs without relying on HT-free reference ICs and can be effectively applied to large complex modern ICs. The unique combination of these characteristics makes the proposed framework more practical for real-world hardware cybersecurity applications as compared with prior art.

show abstract

Knowledge Graph Embedding and Visualization for Pre-Silicon Detection of Hardware Trojans

Cited by 2 publications

References 16 publications

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Netwise Detection of Hardware Trojans Using Scalable Convolution of Graph Embedding Clouds

Contact Info

Product

Resources

About