{"id":"https://openalex.org/W7143444758","doi":"https://doi.org/10.48550/arxiv.2603.26093","title":"ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks","display_name":"ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143444758","doi":"https://doi.org/10.48550/arxiv.2603.26093"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030410591","display_name":"Mohammed Elnawawy","orcid":"https://orcid.org/0000-0002-4367-8060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elnawawy, Mohammed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088488038","display_name":"Gargi Mitra","orcid":"https://orcid.org/0000-0001-8011-4590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitra, Gargi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075654187","display_name":"Shahrear Iqbal","orcid":"https://orcid.org/0000-0001-7819-5715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iqbal, Shahrear","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073641368","display_name":"Karthik Pattabiraman","orcid":"https://orcid.org/0000-0003-2380-3415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pattabiraman, Karthik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9383000135421753,"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":0.9383000135421753,"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":0.020099999383091927,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.010599999688565731,"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/evasion","display_name":"Evasion (ethics)","score":0.7281000018119812},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7044000029563904},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6043000221252441},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5727999806404114},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.54339998960495},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5284000039100647},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4242999851703644}],"concepts":[{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.7281000018119812},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7044000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639000177383423},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48190000653266907},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6240646243095398,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Safety-critical":[0],"domains":[1],"like":[2],"healthcare":[3],"rely":[4],"on":[5,34,86,140,149,158],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"for":[10],"prediction,":[11],"yet":[12],"DNNs":[13],"remain":[14],"vulnerable":[15,80,117],"to":[16,25,81,152],"evasion":[17],"attacks.":[18],"Anomaly":[19],"detectors":[20],"(ADs)":[21],"are":[22,31,78],"widely":[23],"used":[24],"protect":[26],"DNNs,":[27],"but":[28],"conventional":[29],"ADs":[30],"trained":[32],"indiscriminately":[33],"benign":[35],"data":[36,121],"from":[37,122],"all":[38],"patients,":[39,118],"overlooking":[40],"physiological":[41],"differences":[42],"that":[43,66,126],"introduce":[44],"noise,":[45],"degrade":[46],"robustness,":[47],"and":[48,83,96,135],"reduce":[49],"recall.":[50,98],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"ROAST,":[56],"a":[57],"novel":[58],"risk-aware":[59],"outlier":[60],"exposure":[61],"(OE)":[62],"selective":[63],"training":[64,85,112,145],"framework":[65,103],"improves":[67],"AD":[68],"recall":[69,129],"while":[70,142],"largely":[71],"preserving":[72],"precision.":[73,159],"ROAST":[74,127],"identifies":[75],"patients":[76],"who":[77],"less":[79,116],"attack":[82,133,138],"focuses":[84],"these":[87],"cleaner,":[88],"more":[89],"reliable":[90],"data,":[91],"thereby":[92],"reducing":[93,143],"false":[94],"negatives":[95],"improving":[97],"To":[99],"preserve":[100],"precision,":[101],"the":[102,111,115,144],"applies":[104],"OE":[105],"by":[106,130,147],"injecting":[107],"adversarial":[108],"samples":[109],"into":[110],"set":[113],"of":[114],"avoiding":[119],"noisy":[120],"others.":[123],"Experiments":[124],"show":[125],"increases":[128],"16.2\\%":[131],"(black-box":[132],"setting)":[134,139],"5.89\\%":[136],"(white-box":[137],"average":[141,150],"time":[146],"88.3\\%":[148],"compared":[151],"indiscriminate":[153],"training,":[154],"with":[155],"minimal":[156],"impact":[157]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-31T00:00:00"}