{"id":"https://openalex.org/W4414578621","doi":"https://doi.org/10.1007/s10994-025-06896-w","title":"Birds look like cars: adversarial analysis of intrinsically interpretable deep learning","display_name":"Birds look like cars: adversarial analysis of intrinsically interpretable deep learning","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4414578621","doi":"https://doi.org/10.1007/s10994-025-06896-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06896-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06896-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06896-w.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06896-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059946484","display_name":"Hubert Baniecki","orcid":"https://orcid.org/0000-0001-6661-5364"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Hubert Baniecki","raw_affiliation_strings":["University of Warsaw, Warszawa, Poland","Warsaw University of Technology, Warszawa, Poland"],"affiliations":[{"raw_affiliation_string":"University of Warsaw, Warszawa, Poland","institution_ids":["https://openalex.org/I4654613"]},{"raw_affiliation_string":"Warsaw University of Technology, Warszawa, Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049061860","display_name":"Przemys\u0142aw Biecek","orcid":"https://orcid.org/0000-0001-8423-1823"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Przemyslaw Biecek","raw_affiliation_strings":["University of Warsaw, Warszawa, Poland","Warsaw University of Technology, Warszawa, Poland"],"affiliations":[{"raw_affiliation_string":"University of Warsaw, Warszawa, Poland","institution_ids":["https://openalex.org/I4654613"]},{"raw_affiliation_string":"Warsaw University of Technology, Warszawa, Poland","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059946484"],"corresponding_institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4654613"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13522725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"114","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9975000023841858,"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":0.9975000023841858,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9646000266075134,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9581000208854675,"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/adversarial-system","display_name":"Adversarial system","score":0.9002000093460083},{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.821399986743927},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.730400025844574},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.680400013923645},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.656499981880188},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.550599992275238}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9002000093460083},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.821399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7432000041007996},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.730400025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814000010490417},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.680400013923645},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.656499981880188},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.510699987411499},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-025-06896-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06896-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06896-w.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2503.08636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08636","pdf_url":"https://arxiv.org/pdf/2503.08636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2503.08636","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06896-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06896-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06896-w.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322637","display_name":"Politechnika Warszawska","ror":"https://ror.org/00y0xnp53"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414578621.pdf"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W4390787971","https://openalex.org/W4224249813","https://openalex.org/W3174086521","https://openalex.org/W4404345326","https://openalex.org/W4391933803","https://openalex.org/W4399695609","https://openalex.org/W4404660387","https://openalex.org/W3119809428","https://openalex.org/W4396905595","https://openalex.org/W4390956202","https://openalex.org/W1996796871","https://openalex.org/W4402034096","https://openalex.org/W1782368751","https://openalex.org/W2811104224","https://openalex.org/W6948175280","https://openalex.org/W4303712215","https://openalex.org/W4391376610","https://openalex.org/W2951306478","https://openalex.org/W4389519301","https://openalex.org/W2924551358","https://openalex.org/W3016970897","https://openalex.org/W2962843949","https://openalex.org/W2194775991","https://openalex.org/W2913039310","https://openalex.org/W4399739169","https://openalex.org/W4390874717","https://openalex.org/W4403749276","https://openalex.org/W3163176020","https://openalex.org/W3038979745","https://openalex.org/W4311431240","https://openalex.org/W4292753578","https://openalex.org/W4402915716","https://openalex.org/W3196440773","https://openalex.org/W4403759694","https://openalex.org/W4312407344","https://openalex.org/W1526704262","https://openalex.org/W2138011018","https://openalex.org/W2968611394","https://openalex.org/W4307782379","https://openalex.org/W2765813195","https://openalex.org/W4295808856","https://openalex.org/W4312443924","https://openalex.org/W4404314348","https://openalex.org/W3212876771","https://openalex.org/W4283782428","https://openalex.org/W3202897123","https://openalex.org/W2910705748","https://openalex.org/W4385017860","https://openalex.org/W3097858943","https://openalex.org/W4386065251","https://openalex.org/W3172917901","https://openalex.org/W4402288742","https://openalex.org/W4385080308","https://openalex.org/W4400439298","https://openalex.org/W190506616","https://openalex.org/W2803124023","https://openalex.org/W801712705","https://openalex.org/W2568843359","https://openalex.org/W4386076179","https://openalex.org/W2945976633","https://openalex.org/W2117539524","https://openalex.org/W4327656941","https://openalex.org/W4313194958","https://openalex.org/W3167738759","https://openalex.org/W4393161136","https://openalex.org/W4406071635","https://openalex.org/W4393300160","https://openalex.org/W1979769287","https://openalex.org/W4382318444","https://openalex.org/W4404781698","https://openalex.org/W4289129365","https://openalex.org/W4402029569","https://openalex.org/W4214634256","https://openalex.org/W2794825826","https://openalex.org/W4399759300","https://openalex.org/W2963364548","https://openalex.org/W4312010824","https://openalex.org/W3162754606","https://openalex.org/W4308242674","https://openalex.org/W4389991855","https://openalex.org/W4385805086","https://openalex.org/W4401023994","https://openalex.org/W4386075969","https://openalex.org/W4296564518","https://openalex.org/W4361229290"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"A":[1],"common":[2],"belief":[3],"is":[4],"that":[5],"intrinsically":[6],"interpretable":[7,150],"deep":[8,111],"learning":[9],"models":[10,66,90],"ensure":[11],"a":[12,116,123],"correct,":[13],"intuitive":[14],"understanding":[15],"of":[16,59,103,110,119,130,148],"their":[17,134],"behavior":[18],"and":[19,37,54,79,85,136,146],"offer":[20],"greater":[21],"robustness":[22,145],"against":[23,82,92],"accidental":[24],"errors":[25],"or":[26],"intentional":[27],"manipulation.":[28],"However,":[29],"these":[30,60,93],"beliefs":[31],"have":[32],"not":[33],"been":[34],"comprehensively":[35],"verified,":[36],"growing":[38],"evidence":[39],"casts":[40],"doubt":[41],"on":[42,143],"them.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"highlight":[48],"the":[49,96,107,144],"risks":[50],"related":[51],"to":[52,56,115],"overreliance":[53],"susceptibility":[55],"adversarial":[57,74],"manipulation":[58,78],"so-called":[61],"\u201cintrinsically":[62],"(aka":[63],"inherently)":[64],"interpretable\u201d":[65],"by":[67,99,122],"design.":[68],"We":[69],"introduce":[70],"two":[71],"strategies":[72],"for":[73],"analysis":[75],"with":[76],"prototype":[77],"backdoor":[80],"attacks":[81],"prototype-based":[83],"networks,":[84,113],"discuss":[86],"how":[87],"concept":[88],"bottleneck":[89],"defend":[91],"attacks.":[94],"Fooling":[95],"model\u2019s":[97],"reasoning":[98],"exploiting":[100],"its":[101],"use":[102],"latent":[104],"prototypes":[105],"manifests":[106],"inherent":[108],"uninterpretability":[109],"neural":[112],"leading":[114],"false":[117],"sense":[118],"security":[120],"reinforced":[121],"visual":[124],"confirmation":[125],"bias.":[126],"The":[127],"reported":[128],"limitations":[129],"part-prototype":[131],"networks":[132],"put":[133],"trustworthiness":[135],"applicability":[137],"into":[138],"question,":[139],"motivating":[140],"further":[141],"work":[142],"alignment":[147],"(deep)":[149],"models.":[151]},"counts_by_year":[],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-09-28T00:00:00"}