[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82636-en":3,"doc-seo-82636-105":28,"detail-sidebar-cat-0-en-105":89},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},82636,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","VeriChat: Agentic Conversational AI Assistant for Hardware Security Verification","Hardware security verification is a multi-stage engineering effort requiring careful design analysis, threat reasoning, and verification planning, yet verification environments offer limited structured support for security-focused guidance. General chatbots can be unreliable due to hallucinations and static or shallow knowledge. VeriChat is a domain-specialized conversational assistant that supports existing workflows via a retrieval-augmented, multiagent process to improve faithfulness and transparency. It integrates Icarus Verilog, Yosys, and SymbiYosys for RTL syntax checking, synthesis, simulation, and formal verification, and demonstrates strong results on hardware Trojan detection.","This paper will be presented at the 2026 IEEE International Conference on Omni-layer Intelligent Systems (COINS 2026), [https://coinsconf. com/](https://coinsconf. com/) .  \n(Special Session)  \nVeriChat: An Agentic Conversational AI Assistant for Hardware Security Verification  \nDipayan Saha, Khan Thamid Hasan, Shams Tarek, Sujan Kumar Saha, Mark Tehranipoor, and Farimah Farahmandi  \nDepartment of Electrical and Computer Engineering, University of Florida  \nGainesville, FL, USA  \n{dsaha, khanthamidhasan, shams.tarek, [sujansaha](sujansaha}@ufl.edu)[}](sujansaha}@ufl.edu)[@ufl.edu](sujansaha}@ufl.edu), {tehranipoor, [farimah](farimah}@ece.ufl.edu)[}](farimah}@ece.ufl.edu)[@ece.ufl.edu](farimah}@ece.ufl.edu)  \narXiv :2607 .0 1668v 1 [ cs .CR] 2 Jul 2026  \nAbstract—Hardware security verification is a multi-stage process in which engineers must navigate complex design analyses, threat considerations, and verification strategies. They often need security-focused guidance, yet current verification environments provide little structured support for such assistance. Although conversational AI could offer such on-demand assistance, directly using general-purpose chatbots like ChatGPT or Gemini is risky due to their tendency to hallucinate and their reliance on static, outdated knowledge. We present VeriChat, a domain-specialized conversational assistant designed to support, rather than replace, existing verification workflows by providing context-aware security guidance. VeriChat employs a retrieval-augmented, multiagent workflow in which three specialized agents collaboratively minimize hallucinations while improving the transparency and reliability of the response. Beyond question answering, VeriChat integrates open-source EDA tools, including Icarus Verilog, Yosys, and SymbiYosys, to perform syntax checking, synthesis analysis, simulation, and formal verification directly on user-provided RTL designs. Evaluated using a comprehensive methodology, VeriChat achieves a Faithfulness score of 87.73%, significantly outperforming the leading proprietary models. We demonstrate the framework through a hardware Trojan detection case study on an AES S-Box IP, where VeriChat autonomously identifies, simulates, and formally proves a covert key-leakage vulnerability through a multi-turn conversational workflow.  \nKeywords—Hardware Security Verification, Large Language Model, Retrieval-Augmented Generation, EDA Tool Integration  \nI. INTRODUCTION  \nHardware security verification is an incredibly demanding and tedious process that requires immense time and effort. Security verification engineers frequently encounter decision points throughout the verification lifecycle where they must exercise complex security-specific judgments. At many of these points, they would benefit from a helping hand or security-focused guidance. At any stage, they may need to seek ❶ conceptual clarification and reasoning-based assessments, for example, to understand security-relevant design behaviors, interpret threat relevance, or evaluate the soundness of their security properties and assumptions. As they move into planning and execution, they may seek ❷ suggestions on appropriate verification methods, aiming to identify which approaches are  \n979-8-3195-0489-0/26/$31.00 ©2026 IEEE  \nWe thank the U.S. National Science Foundation (NSF) for support through CAREER Award No. 2339971.  \nthe most suitable for addressing specific security concerns. They may also participate in the ❸ development of ideas oriented to security, devising new strategies, rules, or metricsto fill the gaps left by existing approaches. During active verification, they often perform ❹ diagnostic and debugging reasoning to interpret ambiguous or unexpected outcomesand resolve failed checks. Finally, when results are obtained, they must perform ❺ results validation to determine whether the security coverage achieved is sufficient and aligned with accepted practices. Throughout these stages, engineers are r","cbCaikOOux1zR4Kk","https://ap.wps.com/l/cbCaikOOux1zR4Kk","pdf",8008721,1,"English","en",105,"# Introduction\n# VeriChat Approach\n## Multiagent, Retrieval-Augmented Workflow\n## EDA Tool Integration and Verification Pipeline\n# Experimental Evaluation\n## Faithfulness and Comparative Results\n# Case Study","[{\"question\":\"What problem does VeriChat address in hardware security verification?\",\"answer\":\"Hardware security verification involves many decision points where engineers need security-focused guidance, but current environments provide limited structured support, leading to manual, inefficient, and error-prone information gathering.\"},{\"question\":\"Why are general-purpose chatbots risky for this domain?\",\"answer\":\"They may hallucinate by generating incorrect or fabricated content, and they often rely on a static or shallow knowledge base that cannot reliably incorporate newly discovered attacks or evolving verification practices.\"},{\"question\":\"How does VeriChat improve response trustworthiness and verification effectiveness?\",\"answer\":\"VeriChat uses a retrieval-augmented, multiagent workflow with three specialized agents to reduce hallucinations and increase transparency, and it connects open-source EDA tools to perform syntax checking, synthesis, simulation, and formal verification directly on user-provided RTL designs.\"}]",1784181956,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":26},"verichat-agentic-conversational-ai-assistant-for-hardware-security-verification","",{"@graph":34,"@context":83},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/verichat-agentic-conversational-ai-assistant-for-hardware-security-verification/82636/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does VeriChat address in hardware security verification?","Question",{"text":73,"@type":74},"Hardware security verification involves many decision points where engineers need security-focused guidance, but current environments provide limited structured support, leading to manual, inefficient, and error-prone information gathering.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"Why are general-purpose chatbots risky for this domain?",{"text":78,"@type":74},"They may hallucinate by generating incorrect or fabricated content, and they often rely on a static or shallow knowledge base that cannot reliably incorporate newly discovered attacks or evolving verification practices.",{"name":80,"@type":71,"acceptedAnswer":81},"How does VeriChat improve response trustworthiness and verification effectiveness?",{"text":82,"@type":74},"VeriChat uses a retrieval-augmented, multiagent workflow with three specialized agents to reduce hallucinations and increase transparency, and it connects open-source EDA tools to perform syntax checking, synthesis, simulation, and formal verification directly on user-provided RTL designs.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,125,128,132],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":44,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":44,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":44,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":44,"category_name":123,"show_sort_weight":27,"slug":124},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":126,"show_sort_weight":27,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":44,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":44,"category_name":134,"show_sort_weight":104,"slug":135},19,"General","general"]