{"id":"https://openalex.org/W4416036372","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.591","title":"RedHerring Attack: Testing the Reliability of Attack Detection","display_name":"RedHerring Attack: Testing the Reliability of Attack Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036372","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.591"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.591","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.591","pdf_url":"https://aclanthology.org/2025.emnlp-main.591.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.591.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013115158","display_name":"Jonathan Rusert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130184","display_name":"Purdue University Fort Wayne","ror":"https://ror.org/04c4hz115","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130184"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathan Rusert","raw_affiliation_strings":["Purdue University , Fort Wayne"],"affiliations":[{"raw_affiliation_string":"Purdue University , Fort Wayne","institution_ids":["https://openalex.org/I4210130184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013115158"],"corresponding_institution_ids":["https://openalex.org/I4210130184"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18381835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11704","last_page":"11719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.21279999613761902,"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":0.21279999613761902,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.1754000037908554,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.05909999832510948,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.666100025177002},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.29670000076293945},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.29350000619888306},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.24130000174045563},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.23899999260902405}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.666100025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386000275611877},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5284000039100647},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2549000084400177},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24130000174045563},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23899999260902405},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.23330000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.591","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.591","pdf_url":"https://aclanthology.org/2025.emnlp-main.591.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.591","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.591","pdf_url":"https://aclanthology.org/2025.emnlp-main.591.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036372.pdf","grobid_xml":"https://content.openalex.org/works/W4416036372.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"response":[1],"to":[2,14,26,63,73,78,140],"adversarial":[3],"text":[4,17,72],"attacks,":[5],"attack":[6,57,65],"detection":[7,21,66,76,142,174,188],"models":[8,22,33,44,67],"have":[9],"been":[10,48],"proposed":[11],"and":[12,34,53,59,93,172],"shown":[13],"successfully":[15],"identify":[16],"modified":[18],"by":[19,69],"adversaries.Attack":[20],"can":[23],"be":[24],"leveraged":[25],"provide":[27],"an":[28,80,103,154],"additional":[29],"check":[30,162],"for":[31,37],"NLP":[32],"give":[35],"signals":[36],"human":[38,96,114],"input.However,":[39],"the":[40,75,84,91,99,107,113,117,168],"reliability":[41],"of":[42,167],"these":[43],"has":[45],"not":[46],"yet":[47],"thoroughly":[49],"explored.Thus,":[50],"we":[51,157],"propose":[52,158],"test":[54,121],"a":[55,71,88,95,109,159],"novel":[56,123,177],"setting":[58],"attack,":[60,81],"Red-Herring.RedHerring":[61],"aims":[62],"make":[64],"unreliable":[68],"modifying":[70],"cause":[74],"model":[77,125,179],"predict":[79],"while":[82,148],"keeping":[83],"classifier":[85,92,108,152,169],"correct.This":[86],"creates":[87],"tension":[89],"between":[90,144],"detector.If":[94],"sees":[97],"that":[98,136],"detector":[100,118,171],"is":[101,138],"giving":[102],"\"incorrect\"":[104],"prediction,":[105],"but":[106],"correct":[110],"one,":[111],"then":[112],"will":[115],"see":[116],"as":[119],"unreliable.We":[120],"this":[122],"threat":[124,178],"on":[126],"4":[127,133],"datasets":[128],"against":[129],"3":[130],"detectors":[131],"defending":[132],"classifiers.We":[134],"find":[135],"RedHerring":[137],"able":[139],"drop":[141],"accuracy":[143,175],"20":[145],"-71":[146],"points,":[147],"maintaining":[149],"(or":[150],"improving)":[151],"accuracy.As":[153],"initial":[155],"defense,":[156],"simple":[160],"confidence":[161],"which":[163],"requires":[164],"no":[165],"retraining":[166],"or":[170],"increases":[173],"greatly.This":[176],"offers":[180],"new":[181],"insights":[182],"into":[183],"how":[184],"adversaries":[185],"may":[186],"target":[187],"models.":[189]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-08T00:00:00"}