{"id":"https://openalex.org/W4409477972","doi":"https://doi.org/10.1145/3729235","title":"Can Interpretability of Deep Learning Models Detect Textual Adversarial Distribution?","display_name":"Can Interpretability of Deep Learning Models Detect Textual Adversarial Distribution?","publication_year":2025,"publication_date":"2025-04-15","ids":{"openalex":"https://openalex.org/W4409477972","doi":"https://doi.org/10.1145/3729235"},"language":"en","primary_location":{"id":"doi:10.1145/3729235","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729235","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5071889918","display_name":"Ahoud Alhazmi","orcid":"https://orcid.org/0000-0002-3471-8753"},"institutions":[{"id":"https://openalex.org/I199693650","display_name":"Umm al-Qura University","ror":"https://ror.org/01xjqrm90","country_code":"SA","type":"education","lineage":["https://openalex.org/I199693650"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ahoud Alhazmi","raw_affiliation_strings":["Umm Al-Qura University, Makkah, Saudi Arabia","Umm Al-Qura University, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3471-8753","affiliations":[{"raw_affiliation_string":"Umm Al-Qura University, Makkah, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]},{"raw_affiliation_string":"Umm Al-Qura University, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011512844","display_name":"Abdulwahab Aljubairy","orcid":"https://orcid.org/0000-0001-8704-3625"},"institutions":[{"id":"https://openalex.org/I199693650","display_name":"Umm al-Qura University","ror":"https://ror.org/01xjqrm90","country_code":"SA","type":"education","lineage":["https://openalex.org/I199693650"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Abdulwahab Aljubairy","raw_affiliation_strings":["Umm Al-Qura University, Makkah, Saudi Arabia","Umm Al-Qura University, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-8704-3625","affiliations":[{"raw_affiliation_string":"Umm Al-Qura University, Makkah, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]},{"raw_affiliation_string":"Umm Al-Qura University, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070697660","display_name":"Wei Emma Zhang","orcid":"https://orcid.org/0000-0002-0406-5974"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Emma Zhang","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia","The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0406-5974","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"The University of Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080744092","display_name":"Quan Z. Sheng","orcid":"https://orcid.org/0000-0002-3326-4147"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["Macquarie University, Sydney, Australia","Macquarie University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3326-4147","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013668207","display_name":"Elaf Alhazmi","orcid":"https://orcid.org/0009-0003-3550-3898"},"institutions":[{"id":"https://openalex.org/I199693650","display_name":"Umm al-Qura University","ror":"https://ror.org/01xjqrm90","country_code":"SA","type":"education","lineage":["https://openalex.org/I199693650"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Elaf Alhazmi","raw_affiliation_strings":["Umm Al-Qura University, Makkah, Saudi Arabia","Umm Al-Qura University, Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0003-3550-3898","affiliations":[{"raw_affiliation_string":"Umm Al-Qura University, Makkah, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]},{"raw_affiliation_string":"Umm Al-Qura University, Saudi Arabia","institution_ids":["https://openalex.org/I199693650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93501499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T12560","display_name":"Nuclear Engineering Thermal-Hydraulics","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9595000147819519,"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/interpretability","display_name":"Interpretability","score":0.9417563080787659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8919469118118286},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7521532773971558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.728679895401001},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6970646381378174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5380745530128479},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4333050549030304}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9417563080787659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919469118118286},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7521532773971558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.728679895401001},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6970646381378174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5380745530128479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4333050549030304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729235","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729235","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1978662219","https://openalex.org/W2064675550","https://openalex.org/W2163455955","https://openalex.org/W2243397390","https://openalex.org/W2250539671","https://openalex.org/W2560674852","https://openalex.org/W2561975083","https://openalex.org/W2607219512","https://openalex.org/W2741040846","https://openalex.org/W2744095836","https://openalex.org/W2760600531","https://openalex.org/W2788199784","https://openalex.org/W2788403449","https://openalex.org/W2799194071","https://openalex.org/W2905526464","https://openalex.org/W2940009958","https://openalex.org/W2947415936","https://openalex.org/W2949128310","https://openalex.org/W2962772482","https://openalex.org/W2962818281","https://openalex.org/W2963249435","https://openalex.org/W2963615251","https://openalex.org/W2963739340","https://openalex.org/W2963783970","https://openalex.org/W2963859254","https://openalex.org/W2963969878","https://openalex.org/W2963997908","https://openalex.org/W2964082701","https://openalex.org/W2964159205","https://openalex.org/W2964185534","https://openalex.org/W2970078867","https://openalex.org/W2970449623","https://openalex.org/W2982054702","https://openalex.org/W2988194011","https://openalex.org/W2996851481","https://openalex.org/W2998600476","https://openalex.org/W2998682095","https://openalex.org/W3035441470","https://openalex.org/W3035548285","https://openalex.org/W3035736465","https://openalex.org/W3089476752","https://openalex.org/W3089844455","https://openalex.org/W3102720581","https://openalex.org/W3104423855","https://openalex.org/W3105604018","https://openalex.org/W3155936402","https://openalex.org/W3175402282","https://openalex.org/W3176893837","https://openalex.org/W3212257577","https://openalex.org/W4253067820","https://openalex.org/W6695661434"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"are":[4],"widely":[5],"used":[6],"in":[7,38,135],"Natural":[8],"Language":[9],"Processing":[10],"(NLP).":[11],"However,":[12],"adversarial":[13,72,86,117,144,162],"samples":[14,28,73,163],"attack":[15,118,127,167],"benign":[16,90,146],"inputs":[17],"to":[18,103,159],"readily":[19],"fool":[20],"the":[21,76,85,89,93,97,125,136],"DNN":[22],"models.":[23,58,99],"The":[24],"detection":[25],"of":[26,48,78,96,116],"these":[27],"is":[29,151],"a":[30,64],"significant":[31],"challenge":[32],"that":[33],"has":[34],"received":[35],"little":[36],"attention":[37],"textual":[39,71],"domains.":[40],"Existing":[41],"defense":[42],"strategies":[43],"either":[44],"assume":[45],"prior":[46,114],"knowledge":[47,115],"specific":[49],"threats":[50],"or":[51],"do":[52],"not":[53,108],"perform":[54],"well":[55],"on":[56,129],"complex":[57],"In":[59,80],"this":[60],"article,":[61],"we":[62,82],"provide":[63],"new":[65,161],"framework,":[66],"namely":[67],"TADD":[68],"for":[69,92],"detecting":[70],"by":[74,165],"leveraging":[75],"interpretability":[77],"DNNs.":[79],"particular,":[81],"distinguish":[83],"between":[84,143],"distribution":[87,91],"and":[88,106,113,145],"decision":[94],"boundary":[95],"victim":[98,111],"Our":[100],"method":[101,150],"applies":[102],"NLP":[104],"tasks":[105],"does":[107],"require":[109],"re-training":[110],"models":[112],"methods.":[119,168],"We":[120],"evaluate":[121],"our":[122,139,149],"detector":[123],"against":[124,153],"state-of-the-art":[126],"methods":[128],"various":[130],"real-world":[131],"datasets.":[132],"As":[133],"demonstrated":[134],"extensive":[137],"experiments,":[138],"approach":[140],"effectively":[141],"discriminates":[142],"samples.":[147],"Additionally,":[148],"competitive":[152],"unseen":[154],"attacks,":[155],"reflecting":[156],"its":[157],"ability":[158],"discover":[160],"generated":[164],"future":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}