[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85506-en":3,"doc-seo-85506-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85506,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Explainability Methods for Hardware Trojan Detection A Systematic Comparison","Hardware trojans are malicious circuits embedded into integrated-circuit silicon, making them unfixable by software-style security patches and requiring costly product recalls if discovered late. As gate-level detection systems often produce false positives and false negatives, effective hardware security workflows need explainable analysis that supports validation and remediation. This study compares three explainability approaches on the Trust-Hub benchmark: domain-aware property analysis, model-agnostic case-based reasoning, and model-agnostic feature attribution (LIME/SHAP/gradient). Results indicate distinct trade-offs in circuit relevance, correspondence, agreement, and practical efficiency.","arXiv :2601 . 18696v 5 [ cs .LG] 11 Jul 2026  \nExplainability Methods for Hardware Trojan Detection: A Systematic Comparison  \nPaul Whitten 1*, Francis Wolff1† and Chris Papachristou 1†  \n1* Electrical, Computer, and Systems Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, 44106, Ohio, USA.  \n*Corresponding author(s). E-mail(s): [pcw@case.edu](pcw@case.edu) ;  \nContributing authors: [fxw12@case.edu](fxw12@case.edu) ; [cap2@case.edu](cap2@case.edu) ;  \n†These authors contributed equally to this work.  \nAbstract  \nHardware trojans are malicious circuits which compromise the functionality and security of an integrated circuit (IC) . These circuits are manufactured directly into the silicon and cannot be fixed by security patches like software. The solution would require a costly product recall by replacing the IC and hence, early detection in the design process is essential. Hardware detection at best provides statistically based solutions with many false positives and false negatives. These detection methods require more thorough explainable analysis to filter out false indicators.  \nExisting explainability methods developed for general domains like image classification do not always provide the actionable insights hardware engineers need. A question remains: how do domain-aware property analysis, model-agnostic casebased reasoning, and model-agnostic feature attribution techniques compare for hardware security applications?  \nThis work compares three categories of explainability for gate-level hardware trojan detection on the Trust-Hub benchmark dataset: (1) domain-aware property-based analysis of 31 circuit-specific features derived from gate fanin patterns, flip-flop distances, and primary Input/Output (I/O) connectivity; (2) model-agnostic case-based reasoning using k-nearest neighbors for precedentbased explanations; and (3) model-agnostic feature attribution methods (Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), gradient) that provide generic importance scores without circuit-level context.  \nThe findings show that different explainability approaches offer distinct advan  \ntages for hardware security practitioners. The domain-aware property-based method analyzes 31 circuit properties. Detection decisions are explained through  \n1  \nfamiliar concepts like “high fanin complexity near outputs indicates potential trojan triggers.” Case-based reasoning (k-nearest neighbors) achieves 96.51% correspondence between predictions and training exemplars. In contrast, LIME and SHAP show only moderate per-gate agreement (Spearman ρ = 0 .30 mean over n = 11,392 gates, 95% bootstrap CI [0 .29, 0.31]; global concatenated ρ = 0 .31 , p ≪ 10 −300), and yield generic feature importance scores that lack circuit-level context for validation or remediation planning. Detection performance using eXtreme Gradient Boosting (XGBoost) classification with optimized threshold achieves 48.08% precision and 69.44% recall on 11,392 held-out test gates (F1 = 0.568, Matthews Correlation Coefficient (MCC) = 0.575, area under the precision-recall curve (AUPRC) = 0.637) at the optimized threshold of 0.940 .  \nThis represents a 4.25-fold precision improvement over a support vector machine (SVM) baseline reimplemented under identical experimental conditions (11.33% precision, 70.83% recall, F1 = 0.195 at threshold 0.050) with a 7.4-fold reduction in false-positive density (4.74 vs. 35.0 FP per 1,000 gates) . Random Forest achieves comparable F1 (0.555, 58.46% precision, 52.78% recall) with half the false-positive density of XGBoost (2.37 vs. 4.74 FP per 1,000 gates), confirming that the explainable AI (XAI) findings generalize across classifier choices.  \nAdditionally, gradient-based feature attribution (Simonyan et al., 2013), with a speedup factor of 7 over SHAP, yields the same model-agnostic feature weights as SHAP and LIME, confirming that computational efficiency alone cannot subst","cbCaivr84wxNhXZa","https://ap.wps.com/l/cbCaivr84wxNhXZa","pdf",640021,1,37,"English","en",105,"# Abstract\n# Introduction\n## Hardware trojans and the need for circuit-level explanations\n## Explainability approaches compared","[{\"question\":\"Why is explainable analysis important for hardware trojan detection?\",\"answer\":\"Hardware trojans are permanent silicon modifications, and detection models often yield false positives and false negatives. Circuit-grounded explanations are needed so engineers can validate alerts and plan remediation actions.\"},{\"question\":\"What three explainability categories are compared in the study?\",\"answer\":\"The work compares (1) domain-aware property-based analysis using 31 circuit-specific features, (2) model-agnostic case-based reasoning with k-nearest neighbors, and (3) model-agnostic feature attribution methods including LIME, SHAP, and gradient.\"},{\"question\":\"How does domain-aware property analysis differ from feature attribution methods like LIME and SHAP?\",\"answer\":\"Domain-aware property analysis explains decisions using circuit-design concepts tied to circuit properties, while LIME/SHAP provide generic per-feature importance scores that lack circuit-level context for validation and remediation planning.\"}]",1784204062,93,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"explainability-methods-for-hardware-trojan-detection-a-systematic-comparison","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/explainability-methods-for-hardware-trojan-detection-a-systematic-comparison/85506/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is explainable analysis important for hardware trojan detection?","Question",{"text":75,"@type":76},"Hardware trojans are permanent silicon modifications, and detection models often yield false positives and false negatives. Circuit-grounded explanations are needed so engineers can validate alerts and plan remediation actions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What three explainability categories are compared in the study?",{"text":80,"@type":76},"The work compares (1) domain-aware property-based analysis using 31 circuit-specific features, (2) model-agnostic case-based reasoning with k-nearest neighbors, and (3) model-agnostic feature attribution methods including LIME, SHAP, and gradient.",{"name":82,"@type":73,"acceptedAnswer":83},"How does domain-aware property analysis differ from feature attribution methods like LIME and SHAP?",{"text":84,"@type":76},"Domain-aware property analysis explains decisions using circuit-design concepts tied to circuit properties, while LIME/SHAP provide generic per-feature importance scores that lack circuit-level context for validation and remediation planning.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]