{"id":"https://openalex.org/W7160334591","doi":"https://doi.org/10.18653/2026.emnlp-main.171","title":"Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training","display_name":"Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160334591","doi":"https://doi.org/10.18653/2026.emnlp-main.171"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.171","doi":"https://doi.org/10.18653/2026.emnlp-main.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.171","pdf_url":"https://aclanthology.org/2026.emnlp-main.171.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.171.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135316550","display_name":"Wenjing Duan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Duan","raw_affiliation_strings":["Faculty of Electronic and Information Engineering , Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic and Information Engineering , Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135363881","display_name":"Qi Zhou","orcid":"https://orcid.org/0009-0000-9255-0752","observed_orcids":["https://orcid.org/0009-0000-9255-0752"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhou","raw_affiliation_strings":["Faculty of Electronic and Information Engineering , Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic and Information Engineering , Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085696952","display_name":"Yuanfan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanfan Li","raw_affiliation_strings":["Faculty of Electronic and Information Engineering , Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic and Information Engineering , Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25435804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3921","last_page":"3947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9932000041007996,"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":0.9932000041007996,"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/T11644","display_name":"Spam and Phishing Detection","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.00139999995008111,"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/ai-generated-text-detection","display_name":"AI-generated text detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.8709999918937683},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.953000009059906},{"id":"https://openalex.org/keywords/adversarial-examples","display_name":"adversarial examples","score":0.7990000247955322},{"id":"https://openalex.org/keywords/black-box-attacks","display_name":"black-box attacks","score":0.6819999814033508},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9169999957084656},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.968999981880188},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6570000052452087},{"id":"https://openalex.org/keywords/attack-evasion","display_name":"attack evasion","score":0.4259999990463257},{"id":"https://openalex.org/keywords/threat-modeling","display_name":"threat modeling","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8671000003814697},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.8137999773025513},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7922999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605999827384949},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.171","doi":"https://doi.org/10.18653/2026.emnlp-main.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.171","pdf_url":"https://aclanthology.org/2026.emnlp-main.171.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.02374","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.02374","pdf_url":"https://arxiv.org/pdf/2605.02374","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,"listed_in":[],"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.2605.02374","doi":"https://doi.org/10.48550/arxiv.2605.02374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02374","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.171","doi":"https://doi.org/10.18653/2026.emnlp-main.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.171","pdf_url":"https://aclanthology.org/2026.emnlp-main.171.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160334591.pdf","grobid_xml":"https://content.openalex.org/works/W7160334591.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412886760","https://openalex.org/W7158237452","https://openalex.org/W4406678677","https://openalex.org/W4396914143","https://openalex.org/W7131867376","https://openalex.org/W7221109101","https://openalex.org/W4414460072","https://openalex.org/W4412945222","https://openalex.org/W7220915169","https://openalex.org/W4414921166"],"abstract_inverted_index":{"Machine-generated":[0],"text":[1],"(MGT)":[2],"detection":[3,143],"is":[4],"critical":[5],"for":[6],"regulating":[7],"online":[8],"information":[9],"ecosystems,":[10],"yet":[11],"existing":[12],"detectors":[13,151],"often":[14],"fail":[15],"under":[16,30,59,158],"limited":[17],"fresh":[18],"supervision":[19],"and":[20,34,37,70,105,134,152],"humanization-oriented":[21],"attacks.We":[22],"study":[23],"this":[24,75],"problem":[25],"as":[26,54],"few-shot":[27,88],"robustness":[28,89],"recovery":[29],"evolving":[31],"generators,":[32],"domains,":[33],"attack":[35,155],"patterns,":[36],"use":[38],"threat":[39],"modeling":[40],"to":[41,96,115],"diagnose":[42],"detector":[43,108],"failures":[44],"from":[45,101],"an":[46],"attacker's":[47],"viewpoint.We":[48],"identify":[49],"unstable":[50],"local":[51,118],"boundary":[52,112],"estimation":[53],"a":[55,86,92,110,124],"key":[56],"failure":[57],"mode:":[58],"scarce":[60],"supervision,":[61],"humanized":[62,99],"MGT":[63],"can":[64],"induce":[65],"prediction":[66],"flips,":[67],"logit":[68],"drift,":[69],"clean-adversarial":[71,117],"representation":[72],"misalignment.To":[73],"address":[74],"issue,":[76],"we":[77],"propose":[78],"RAG-GuidEd":[79],"Attacker":[80],"Strengthens":[81],"ConTrastive":[82],"Few-shot":[83],"Detector":[84],"(REACT),":[85],"threat-aware":[87],"framework.REACT":[90],"uses":[91],"dynamic":[93],"retrieval-guided":[94],"attacker":[95],"generate":[97],"boundary-oriented":[98],"rewrites":[100],"extreme":[102],"positive-negative":[103],"anchors,":[104],"trains":[106],"the":[107],"with":[109,130],"pairwise":[111],"contrastive":[113],"objective":[114],"stabilize":[116],"geometry.Alternating":[119],"attacker-detector":[120],"updates":[121],"further":[122],"form":[123],"co-evolutionary":[125],"curriculum.Experiments":[126],"on":[127],"4":[128,131,159],"datasets":[129],"shot":[132],"sizes":[133],"3":[135],"random":[136],"seeds":[137],"show":[138],"that":[139],"REACT":[140],"improves":[141],"average":[142,154],"F1":[144],"by":[145,162],"4.95":[146],"points":[147],"over":[148],"8":[149],"SOTA":[150],"reduces":[153],"success":[156],"rate":[157],"strong":[160],"attacks":[161],"3.66":[163],"percentage":[164],"points.":[165]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-05-06T00:00:00"}