{"id":"https://openalex.org/W7128314953","doi":"https://doi.org/10.1109/mcom.001.2500229","title":"When Feature Attribution Methods Meet Robust Models: A Survey and Outlook","display_name":"When Feature Attribution Methods Meet Robust Models: A Survey and Outlook","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128314953","doi":"https://doi.org/10.1109/mcom.001.2500229"},"language":"en","primary_location":{"id":"doi:10.1109/mcom.001.2500229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500229","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2031/2a5a023e-45e0-417a-9d4a-a8e33b4c71d5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125364982","display_name":"Yuchen Liu","orcid":null},"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":"Yuchen Liu","raw_affiliation_strings":["Ministry of Education, School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education, School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125353679","display_name":"Yunjie Ge","orcid":null},"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":"Yunjie Ge","raw_affiliation_strings":["Institute for Math&#x0026;AI, Wuhan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Math&#x0026;AI, Wuhan University,China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":0.13427573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"64","issue":"6","first_page":"104","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08250000327825546,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08250000327825546,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.05950000137090683,"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/T10057","display_name":"Face and Expression Recognition","score":0.05620000138878822,"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/feature","display_name":"Feature (linguistics)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38589999079704285},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.36820000410079956},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.34850001335144043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30970001220703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4081000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39649999141693115},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mcom.001.2500229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500229","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Magazine","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/2a5a023e-45e0-417a-9d4a-a8e33b4c71d5","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/2a5a023e-45e0-417a-9d4a-a8e33b4c71d5","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, Y & Ge, Y 2026, 'When Feature Attribution Methods Meet Robust Models: A Survey and Outlook', IEEE Communications Magazine. https://doi.org/10.1109/MCOM.001.2500229","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/2a5a023e-45e0-417a-9d4a-a8e33b4c71d5","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/2a5a023e-45e0-417a-9d4a-a8e33b4c71d5","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, Y & Ge, Y 2026, 'When Feature Attribution Methods Meet Robust Models: A Survey and Outlook', IEEE Communications Magazine. https://doi.org/10.1109/MCOM.001.2500229","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3194357009","display_name":null,"funder_award_id":"62502350,62441237","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8640288923","display_name":null,"funder_award_id":"GZB20250384","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"black-box":[1],"nature":[2],"of":[3,11,60,82,154],"deep":[4],"neural":[5],"networks":[6],"has":[7],"motivated":[8],"the":[9,56,150,179],"development":[10],"explanation":[12],"methods":[13,35,62,85,120],"to":[14,157],"improve":[15],"model":[16],"transparency.":[17],"Among":[18],"them,":[19],"feature":[20],"attribution":[21,114,167],"(FA)":[22],"is":[23],"widely":[24],"adopted":[25],"for":[26,165],"its":[27],"intuitive":[28],"outputs":[29],"and":[30,76,100,116,127,129,136,144,152,169,176,183],"broad":[31],"applicability.":[32],"While":[33],"FA":[34,61,84,156],"have":[36],"been":[37],"extensively":[38],"evaluated":[39],"on":[40,45,67],"standard":[41,91],"models,":[42],"their":[43],"behavior":[44],"adversarially":[46],"robust":[47,64,131,158],"models":[48,132],"remains":[49],"unclear.":[50],"To":[51],"address":[52],"this,":[53],"we":[54,105],"present":[55],"first":[57],"systematic":[58],"study":[59],"under":[63,125],"training,":[65,92],"focusing":[66],"five":[68],"key":[69,108],"properties:":[70],"fidelity,":[71],"stability,":[72],"conciseness,":[73],"class":[74,134],"sensitivity,":[75,138],"weight":[77,137],"sensitivity.":[78],"Through":[79],"quantitative":[80],"evaluation":[81],"six":[83],"across":[86],"four":[87],"training":[88,94,171],"strategies,":[89],"i.e.,":[90],"adversarial":[93,96,101],"(AT),":[95],"robustness":[97,102,111,143],"distillation":[98],"(ARD),":[99],"regularization":[103],"(ARR),":[104],"reveal":[106],"several":[107],"findings:":[109],"(1)":[110],"significantly":[112],"improves":[113],"fidelity":[115],"stability;":[117],"(2)":[118],"white-box":[119],"yield":[121],"more":[122],"concise":[123],"explanations":[124],"AT":[126],"ARD;":[128],"(3)":[130],"reduce":[133],"sensitivity":[135],"indicating":[139],"a":[140],"trade-off":[141],"between":[142],"interpretability.":[145],"These":[146],"insights":[147],"highlight":[148],"both":[149],"benefits":[151],"limitations":[153],"applying":[155],"models.":[159],"We":[160],"conclude":[161],"by":[162],"outlining":[163],"directions":[164],"robustness-aware":[166],"techniques":[168],"joint":[170],"strategies":[172],"that":[173],"balance":[174],"interpretability":[175],"security,":[177],"paving":[178],"way":[180],"toward":[181],"trustworthy":[182],"explainable":[184],"artificial":[185],"intelligence":[186],"systems.<br/>":[187]},"counts_by_year":[],"updated_date":"2026-06-05T06:17:00.636019","created_date":"2026-02-09T00:00:00"}