{"id":"https://openalex.org/W7203742425","doi":"https://doi.org/10.48550/arxiv.2608.17836","title":"Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs","display_name":"Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203742425","doi":"https://doi.org/10.48550/arxiv.2608.17836"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17836","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17836","pdf_url":"https://arxiv.org/pdf/2608.17836","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153542678","display_name":"Roman Maksimov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maksimov, Roman","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120534259","display_name":"Vladimir Igorevich Aletov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aletov, Vladimir","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099097234","display_name":"Vladimir Solodkin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Solodkin, Vladimir","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114403023","display_name":"Dmitry Bylinkin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bylinkin, Dmitry","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093734243","display_name":"Daniil Olegovich Medyakov","orcid":"https://orcid.org/0009-0003-2007-8446","observed_orcids":["https://orcid.org/0009-0003-2007-8446"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Medyakov, Daniil","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125178809","display_name":"Aleksandr Beznosikov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Beznosikov, Aleksandr","raw_affiliation_strings":["Basic Research of Artificial Intelligence Laboratory","Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic Research of Artificial Intelligence Laboratory","institution_ids":[]},{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/white-box-attacks","display_name":"white-box attacks","score":0.9049999713897705},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/knowledge-editing","display_name":"knowledge editing","score":0.9729999899864197},{"id":"https://openalex.org/keywords/constraint-removal","display_name":"constraint removal","score":0.6830000281333923},{"id":"https://openalex.org/keywords/adversarial-attacks","display_name":"adversarial attacks","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437000274658203},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3716999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17836","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17836","pdf_url":"https://arxiv.org/pdf/2608.17836","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17836","doi":"https://doi.org/10.48550/arxiv.2608.17836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17836","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.17836","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17836","pdf_url":"https://arxiv.org/pdf/2608.17836","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203742425.pdf","grobid_xml":"https://content.openalex.org/works/W7203742425.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415036360","https://openalex.org/W7166854516","https://openalex.org/W7128682396","https://openalex.org/W4391832655","https://openalex.org/W7137801986","https://openalex.org/W4393063446","https://openalex.org/W6979300360","https://openalex.org/W4412876878","https://openalex.org/W7165679523","https://openalex.org/W7212035096"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,44],"(LLMs)":[4],"are":[5],"granted":[6],"increasing":[7],"autonomy,":[8],"it":[9],"is":[10,38,63],"essential":[11],"to":[12,50,56,87,96,118],"investigate":[13],"methods":[14,113],"that":[15,43,62],"can":[16],"induce":[17],"unsafe":[18],"behavior.":[19],"We":[20,69],"propose":[21],"a":[22,60,99],"novel":[23],"white-box":[24],"attack":[25,109],"inspired":[26],"by":[27,40,74],"locate-then-edit":[28],"approaches":[29],"from":[30,80,98],"the":[31,41,57,71,81],"field":[32],"of":[33],"Knowledge":[34],"Editing.":[35],"Our":[36],"choice":[37],"motivated":[39],"observation":[42],"edited":[45],"with":[46,103],"such":[47],"schemes":[48],"tend":[49],"assign":[51],"unusually":[52],"high":[53],"prediction":[54],"probabilities":[55],"edit":[58],"target,":[59],"property":[61],"particularly":[64],"advantageous":[65],"when":[66],"designing":[67],"attacks.":[68],"modify":[70],"editing":[72],"framework":[73],"incorporating":[75],"as-":[76],"sociative":[77],"knowledge":[78],"retrieved":[79],"model,":[82],"thereby":[83],"extending":[84],"constraint":[85],"removal":[86],"an":[88],"entire":[89],"thematic":[90],"category":[91],"rather":[92],"than":[93],"being":[94],"limited":[95],"prompts":[97],"predefined":[100],"dataset.":[101],"Experiments":[102],"various":[104],"archi-":[105],"tectures":[106],"demonstrate":[107],"improved":[108],"effectiveness":[110],"over":[111],"competing":[112],"without":[114],"dealing":[115],"critical":[116],"damage":[117],"general":[119],"model":[120],"performance.":[121]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-20T00:00:00"}