{"id":"https://openalex.org/W4416550319","doi":"https://doi.org/10.1145/3719027.3744829","title":"Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis via Intermediate Representation and Language Model","display_name":"Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis via Intermediate Representation and Language Model","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416550319","doi":"https://doi.org/10.1145/3719027.3744829"},"language":"en","primary_location":{"id":"doi:10.1145/3719027.3744829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3719027.3744829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.17162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002308559","display_name":"Side Liu","orcid":"https://orcid.org/0009-0003-8106-4101"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Side Liu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-8106-4101","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101420644","display_name":"Jiang Ming","orcid":"https://orcid.org/0000-0001-9682-0502"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang Ming","raw_affiliation_strings":["Tulane University, New Orleans, USA"],"raw_orcid":"https://orcid.org/0000-0001-9682-0502","affiliations":[{"raw_affiliation_string":"Tulane University, New Orleans, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032682556","display_name":"Guodong Zhou","orcid":"https://orcid.org/0009-0005-8491-273X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Zhou","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0005-8491-273X","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyi Liu","orcid":"https://orcid.org/0009-0003-3987-088X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Liu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-3987-088X","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074852104","display_name":"Jianming Fu","orcid":"https://orcid.org/0000-0002-4639-5824"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Fu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4639-5824","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076621366","display_name":"Guojun Peng","orcid":"https://orcid.org/0000-0001-5731-8958"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Peng","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5731-8958","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002308559"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41806174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0031999999191612005,"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/T11424","display_name":"Security and Verification in Computing","score":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.723800003528595},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5802000164985657},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4684999883174896},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.415800005197525},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38929998874664307},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.365200012922287},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115000128746033},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.723800003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635200023651123},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5802000164985657},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5357000231742859},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3719027.3744829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3719027.3744829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.17162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17162","pdf_url":"https://arxiv.org/pdf/2506.17162","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.17162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17162","pdf_url":"https://arxiv.org/pdf/2506.17162","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6009368860","display_name":null,"funder_award_id":"2312185, 2417055","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G793964153","display_name":null,"funder_award_id":"62172308, 62272351, 61972297, 62172144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320310142","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1972531058","https://openalex.org/W1988146703","https://openalex.org/W2014466911","https://openalex.org/W2038296020","https://openalex.org/W2082190528","https://openalex.org/W2089554624","https://openalex.org/W2525598640","https://openalex.org/W2573650634","https://openalex.org/W2574797807","https://openalex.org/W2575541032","https://openalex.org/W2749572357","https://openalex.org/W2886694146","https://openalex.org/W2926178846","https://openalex.org/W3133719257","https://openalex.org/W4212780327","https://openalex.org/W4287644588","https://openalex.org/W4288104392","https://openalex.org/W4385269993"],"related_works":[],"abstract_inverted_index":{"Malicious":[0],"PDF":[1,21,51,94,98,115,153,190],"files":[2],"have":[3,24,44],"emerged":[4],"as":[5],"a":[6,11,90,124],"persistent":[7],"threat":[8],"and":[9,97,151,159],"become":[10],"popular":[12],"attack":[13],"vector":[14],"in":[15],"web-based":[16],"attacks.":[17],"While":[18],"machine":[19,71],"learning-based":[20],"malware":[22,99,154,191],"classifiers":[23,28],"shown":[25],"promise,":[26],"these":[27,54,60,74],"are":[29],"often":[30],"susceptible":[31],"to":[32,46,77,135,149,188],"adversarial":[33,171],"attacks,":[34],"undermining":[35],"their":[36],"reliability.":[37],"To":[38,85],"address":[39],"this":[40],"issue,":[41],"recent":[42],"studies":[43,61],"aimed":[45],"enhance":[47],"the":[48,56,67,80,103],"robustness":[49,172],"of":[50,69,82,181],"classifiers.":[52,192],"Despite":[53],"efforts,":[55],"feature":[57,83,95],"engineering":[58],"underlying":[59],"remains":[62],"outdated.":[63],"Consequently,":[64],"even":[65],"with":[66],"application":[68],"cutting-edge":[70],"learning":[72],"techniques,":[73],"approaches":[75],"fail":[76],"fundamentally":[78],"resolve":[79],"issue":[81],"instability.":[84],"tackle":[86],"this,":[87],"we":[88,119,129],"propose":[89],"novel":[91],"approach":[92,146],"for":[93,114],"extraction":[96],"detection.":[100],"We":[101],"introduce":[102],"PDFObj":[104],"IR":[105],"(PDF":[106],"Object":[107,132],"Intermediate":[108],"Representation),":[109],"an":[110,131,175],"assembly-like":[111],"language":[112,126],"framework":[113],"objects,":[116],"from":[117,141],"which":[118],"extract":[120],"semantic":[121,158],"features":[122],"using":[123],"pretrained":[125],"model.":[127],"Additionally,":[128],"construct":[130],"Reference":[133],"Graph":[134],"capture":[136],"structural":[137,160],"features,":[138],"drawing":[139],"inspiration":[140],"program":[142],"analysis.":[143],"This":[144],"dual":[145],"enables":[147],"us":[148],"analyze":[150],"detect":[152],"based":[155],"on":[156,184],"both":[157],"features.":[161],"Experimental":[162],"results":[163],"demonstrate":[164],"that":[165],"our":[166],"proposed":[167],"classifier":[168],"achieves":[169],"strong":[170],"while":[173],"maintaining":[174],"exceptionally":[176],"low":[177],"false":[178],"positive":[179],"rate":[180],"only":[182],"0.07%":[183],"baseline":[185],"dataset":[186],"compared":[187],"state-of-the-art":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}