{"id":"https://openalex.org/W4416398204","doi":"https://doi.org/10.18653/v1/2026.findings-acl.863","title":"Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs","display_name":"Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416398204","doi":"https://doi.org/10.18653/v1/2026.findings-acl.863"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.863","pdf_url":"https://aclanthology.org/2026.findings-acl.863.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.863.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120413892","display_name":"Man Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Man Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120365945","display_name":"Xinyi Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120365946","display_name":"Zuofeng Suo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhufeng Suo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120365947","display_name":"Jinbo Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinbo Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120413893","display_name":"Linghui Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linghui Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120460655","display_name":"Yanhao Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhao Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120460656","display_name":"Anh Tuan Luu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh Tuan Luu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120460657","display_name":"Shuai Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Zhao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02532184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17437","last_page":"17456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.33970001339912415,"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":0.33970001339912415,"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/T10028","display_name":"Topic Modeling","score":0.13729999959468842,"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":0.09520000219345093,"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/backdoor","display_name":"Backdoor","score":0.9976000189781189},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7208999991416931},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5480999946594238},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5370000004768372},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9976000189781189},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7208999991416931},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6516000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5552999973297119},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2786000072956085},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2662999927997589}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.863","pdf_url":"https://aclanthology.org/2026.findings-acl.863.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07697","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07697","pdf_url":"https://arxiv.org/pdf/2510.07697","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07697","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.863","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.863","pdf_url":"https://aclanthology.org/2026.findings-acl.863.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416398204.pdf","grobid_xml":"https://content.openalex.org/works/W4416398204.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,68],"rise":[2],"of":[3,42,76],"advanced":[4],"reasoning":[5,15,46,60],"capabilities,":[6],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"are":[11],"receiving":[12],"increasing":[13],"attention.While":[14],"enhances":[16],"LLMs'":[17],"performance":[18],"on":[19,53],"downstream":[20],"tasks,":[21],"it":[22],"also":[23,115],"introduces":[24],"new":[25,95],"threat":[26],"vectors,":[27],"as":[28],"adversaries":[29],"can":[30],"leverage":[31],"these":[32],"capabilities":[33],"to":[34],"conduct":[35],"backdoor":[36,43,54,78,108],"attacks.Prior":[37],"surveys":[38],"provide":[39],"broad":[40],"overviews":[41],"attacks":[44,55,79,109,120],"and":[45,56,89,113,121],"security;":[47],"however,":[48],"a":[49,73,94,99],"systematic":[50],"survey":[51],"focused":[52],"defenses":[57,117],"against":[58,118],"LLM":[59],"is":[61],"still":[62],"absent.In":[63],"this":[64],"paper,":[65],"we":[66,92],"take":[67],"first":[69],"step":[70],"toward":[71],"providing":[72],"comprehensive":[74],"review":[75],"reasoning-based":[77,107],"in":[80],"LLMs":[81],"by":[82],"analyzing":[83],"their":[84],"underlying":[85],"mechanisms,":[86],"methodological":[87],"frameworks,":[88],"unresolved":[90],"challenges.Specifically,":[91],"introduce":[93],"taxonomy":[96],"that":[97],"offers":[98],"unified":[100],"perspective":[101],"for":[102],"summarizing":[103],"existing":[104],"approaches,":[105],"categorizing":[106],"into":[110],"associative,":[111],"passive,":[112],"active.We":[114],"summarize":[116],"such":[119],"discuss":[122],"current":[123],"challenges":[124],"alongside":[125],"future":[126],"research":[127],"directions.":[128]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-11T00:00:00"}