{"id":"https://openalex.org/W7135212548","doi":"https://doi.org/10.1109/iccp68926.2025.11427115","title":"CTF-PWN100: Automated Binary Exploitation of CTF Challenges Leveraging Large Language Models","display_name":"CTF-PWN100: Automated Binary Exploitation of CTF Challenges Leveraging Large Language Models","publication_year":2025,"publication_date":"2025-10-16","ids":{"openalex":"https://openalex.org/W7135212548","doi":"https://doi.org/10.1109/iccp68926.2025.11427115"},"language":null,"primary_location":{"id":"doi:10.1109/iccp68926.2025.11427115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp68926.2025.11427115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129076586","display_name":"Tudor Cristea","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Tudor Cristea","raw_affiliation_strings":["Technical University of Cluj-Napoca,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Department of Computer Science","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006746992","display_name":"Radu-Marian Portase","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Radu-Marian Portase","raw_affiliation_strings":["Bitdefender Technical University of Cluj-Napoca"],"affiliations":[{"raw_affiliation_string":"Bitdefender Technical University of Cluj-Napoca","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128995161","display_name":"Adrian Cole\u015fa","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adrian Cole\u015fa","raw_affiliation_strings":["Technical University of Cluj-Napoca Bitdefender"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca Bitdefender","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5129076586"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88336045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.20270000398159027,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.20270000398159027,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20250000059604645,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09130000323057175,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4300999939441681},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3630000054836273},{"id":"https://openalex.org/keywords/binary-data","display_name":"Binary data","score":0.34540000557899475},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.31929999589920044},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.30959999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564000248908997},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp68926.2025.11427115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp68926.2025.11427115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"CTF-PWN100,":[5],"a":[6,41],"dataset":[7,45],"and":[8,37,43,64,75,95,119],"automated":[9,68],"framework":[10,70],"designed":[11],"to":[12],"evaluate":[13],"the":[14,31,82,120],"performance":[15],"of":[16,33,47,88,122],"large":[17],"language":[18],"models":[19,84],"(LLMs)":[20],"in":[21,108],"solving":[22],"Capture-The-Flag":[23],"(CTF)":[24],"binary":[25,49],"exploitation":[26,50],"challenges.":[27],"We":[28],"specifically":[29],"assess":[30],"capabilities":[32],"DeepSeek-R1,":[34],"Gemini-2.5-Pro":[35],"(Preview),":[36],"Gemini-2.5-Flash":[38],"(Preview)":[39],"on":[40],"balanced":[42],"diverse":[44],"consisting":[46],"100":[48],"problems":[51],"covering":[52],"multiple":[53],"vulnerability":[54,117],"types,":[55],"including":[56],"Buffer":[57],"Overflow,":[58,62],"Format":[59],"String,":[60],"Heap":[61],"Use-After-Free,":[63],"Miscellaneous.":[65],"Using":[66],"an":[67],"evaluation":[69],"integrating":[71],"decompilation,":[72],"code":[73],"filtering,":[74],"dynamic":[76],"feedback":[77],"from":[78],"Python-generated":[79],"exploit":[80,124],"scripts,":[81],"three":[83],"achieved":[85],"success":[86],"rates":[87],"${5":[89],"1":[90],"\\%},":[91],"{6":[92],"6":[93],"\\%}$,":[94],"$46":[96],"\\%$,":[97],"respectively.":[98],"The":[99],"results":[100],"indicate":[101],"that":[102],"reasoning-oriented":[103],"LLMs":[104],"demonstrate":[105],"promising":[106],"potential":[107],"addressing":[109],"complex":[110],"cybersecurity":[111],"tasks.":[112],"However,":[113],"limitations":[114],"persist":[115],"regarding":[116],"identification":[118],"development":[121],"sophisticated":[123],"scripts.":[125]},"counts_by_year":[],"updated_date":"2026-03-15T07:15:06.534987","created_date":"2026-03-14T00:00:00"}