[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117790-en":3,"doc-seo-117790-105":30,"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":4,"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":27,"seo_description":14,"update_tm":28,"read_time":29},117790,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","A Security Verification Framework of Cryptographic Protocols Using Machine Learning","A security verification framework for cryptographic protocols uses machine learning to overcome limitations of formal verification. Formal methods can require large computational time and may not guarantee decidability. The proposed approach aims for verification time linear in protocol size by training models on labeled protocol datasets. Since labeled data are scarce, the framework generates large datasets by automatically producing random protocols and labeling them via formal verification tools. It also employs a neural network that models protocol series and tree structures, then evaluates the method on practical cryptographic protocols.","A Security Verification Framework of Cryptographic Protocols  \nUsing Machine Learning  \nKentaro Ohno  \nNTT Computer & Data Science Laboratories  \nMisato Nakabayashi NTT Social Informatics Laboratories  \narXiv :2304 . 13249v1 [ cs .CR] 26 Apr 2023  \nAbstract  \nWe propose a security verification framework for cryptographic protocols using machine learning. In recent years, as cryptographic protocols have become more complex, research on automatic verification techniques has been focused on. The main technique is formal verification. However, the formal verification has two problems: it requires a large amount of computational time and does not guarantee decidability. We propose a method that allows security verification with computational time on the order of linear with respect to the size of the protocol using machine learning. In training machine learning models for security verification of cryptographic protocols, a sufficient amount of data, i.e., a set of protocol data with security labels, is difficult to collect from academic papers and other sources. To overcome this issue, we propose away to create arbitrarily large datasets by automatically generating random protocols and assigning security labels to them using formal verification tools. Furthermore, to exploit structural features of protocols, we construct a neural network that processes a protocol along its series and tree structures. We evaluate the proposed method by applying it to verification of practical cryptographic protocols.  \n1 Introduction  \nToday, cryptographic protocols are used in a variety of important situations and are indispensable technologies. For example, TLS 1.3 is used for confidentiality, tamper detection, and authentication of communication partners on the Internet [39] . Vulnerabilities in cryptographic protocols can compromise communications over the Internet and tamper with electronic transactions. The impact is serious, and therefore the security of cryptographic protocols is important. However, the design of cryptographic protocols is generally complex and error-prone.  \nTo design complex and correct cryptographic protocols, designers often use computer aids such as automated verification tools. As we input the protocol specification and  \nsecurity requirements, an ideal automated verification tool instantly outputs whether the protocol satisfies the security requirements or not. A typical example of such an automatic verification tool is a formal verification tool based on model checking. Formal verification is a technique that describes a target using a formal language and verifies whether or not the target satisfies certain requirements by using mathematical techniques. In particular, formal verification tools based on model checking provide exhaustive verification by thoroughly enumerating possible states of the target and verifying all possible paths to the target. There are many formal verification tools for cryptographic protocols; ProVerif [8, 10] and Tamarin prover [3, 38] are well-known examples. These tools are used in the design of widely used cryptographic protocols and contribute to the design of secure protocols. For example, formal verification tools were used in the standardization process of TLS 1.3 and 5G authentication protocols, and many vulnerabilities were found by these tools [4, 5, 7, 9, 22, 24–27, 47] . As shown in these examples, the strength of formal verification tools is that they can find vulnerabilities that are difficult for the human eye to detect.  \nThe problem with formal verification is the time required to perform exhaustive verification. In addition, verification may never be completed because the verification tools do not have decidability [29, 43] . For example, the TLS verification by Bhargavan et al. [7] took up to 35 hours. Therefore, theverifier should devise ways to formalize the protocol and use the tools to complete the verification within the effective time. This requires high-level expertise. This is one reason that many ","cbCaiu3184LNo6qd","https://ap.wps.com/l/cbCaiu3184LNo6qd","pdf",574974,1,14,"English","en",105,"# Introduction\n## Motivation and limitations of formal verification\n## Machine learning-based verification approach\n## Data generation and protocol representation","[{\"question\":\"Why does the framework move beyond formal verification for cryptographic protocols?\",\"answer\":\"Formal verification can be computationally expensive and may not terminate due to lack of decidability. The framework targets practical verification time and improved usability.\"},{\"question\":\"How does the framework obtain training data with security labels?\",\"answer\":\"It automatically generates random protocols and assigns security labels using formal verification tools, enabling construction of arbitrarily large labeled datasets.\"},{\"question\":\"What neural network structure is used to exploit protocol features?\",\"answer\":\"A neural network processes protocols using both series and tree structures, capturing hierarchical information such as the order of cryptographic operations.\"}]","A Security Verification Framework of Cryptographic Protocols Using Machine Learning | PDF",1785679590,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-security-verification-framework-of-cryptographic-protocols-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-security-verification-framework-of-cryptographic-protocols-using-machine-learning/117790/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does the framework move beyond formal verification for cryptographic protocols?","Question",{"text":75,"@type":76},"Formal verification can be computationally expensive and may not terminate due to lack of decidability. The framework targets practical verification time and improved usability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the framework obtain training data with security labels?",{"text":80,"@type":76},"It automatically generates random protocols and assigns security labels using formal verification tools, enabling construction of arbitrarily large labeled datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"What neural network structure is used to exploit protocol features?",{"text":84,"@type":76},"A neural network processes protocols using both series and tree structures, capturing hierarchical information such as the order of cryptographic operations.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"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":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]