{"id":"https://openalex.org/W7138992473","doi":"https://doi.org/10.1609/aaai.v40i44.41149","title":"DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt","display_name":"DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138992473","doi":"https://doi.org/10.1609/aaai.v40i44.41149"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i44.41149","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41149","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41149/45110","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41149/45110","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115597071","display_name":"Yitong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitong Zhang","raw_affiliation_strings":["College of AI, Tsinghua University\nSchool of Computer Science and Engineering, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of AI, Tsinghua University\nSchool of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129822542","display_name":"Jia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["College of AI, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of AI, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liyi Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyi Cai","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129972487","display_name":"Ge Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"40","issue":"44","first_page":"38111","last_page":"38119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4106999933719635,"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":0.4106999933719635,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.28299999237060547,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0478999987244606,"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/key","display_name":"Key (lock)","score":0.527400016784668},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47189998626708984},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35190001130104065},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.3093000054359436},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.2818000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709000110626221},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5083000063896179},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i44.41149","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41149","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41149/45110","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i44.41149","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41149","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41149/45110","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138992473.pdf","grobid_xml":"https://content.openalex.org/works/W7138992473.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"achieved":[5],"impressive":[6],"progress":[7],"across":[8],"various":[9],"applications":[10],"but":[11],"remain":[12],"vulnerable":[13],"to":[14,23,81,101,147],"malicious":[15,25,103,118],"queries.":[16],"Existing":[17],"safety":[18,85],"alignment":[19,107],"approaches":[20],"typically":[21],"fail":[22],"resist":[24],"queries":[26,119],"while":[27,120],"preserving":[28,121],"utility":[29],"on":[30],"benign":[31,122],"ones":[32],"effectively.":[33],"To":[34],"address":[35],"these":[36],"challenges,":[37],"we":[38,49,74],"propose":[39,75],"DAVSP,":[40],"which":[41,54],"is":[42],"built":[43],"upon":[44],"two":[45],"key":[46],"innovations.":[47],"First,":[48],"introduce":[50],"Visual":[51,139],"Safety":[52,140],"Prompt,":[53],"appends":[55],"a":[56,78],"trainable":[57],"padding":[58],"region":[59],"around":[60],"the":[61,70,83,90,96,138,148],"input":[62,123],"image.":[63],"It":[64,94],"preserves":[65],"visual":[66,84],"features":[67],"and":[68,142],"expands":[69],"optimization":[71],"space.":[72,93],"Second,":[73],"Deep":[76,143],"Alignment,":[77],"novel":[79],"approach":[80],"train":[82],"prompt":[86],"through":[87],"supervision":[88],"in":[89],"model's":[91],"activation":[92],"enhances":[95],"inherent":[97],"ability":[98],"of":[99],"LVLMs":[100],"perceive":[102],"queries,":[104],"achieving":[105],"deeper":[106],"than":[108],"prior":[109],"works.":[110],"Extensive":[111],"experiments":[112],"demonstrate":[113],"that":[114,136],"DAVSP":[115,126],"effectively":[116],"resists":[117],"utility.":[124],"Furthermore,":[125],"exhibits":[127],"great":[128],"cross-model":[129],"generation":[130],"ability.":[131],"Ablation":[132],"studies":[133],"further":[134],"reveal":[135],"both":[137],"Prompt":[141],"Alignment":[144],"are":[145],"essential":[146],"overall":[149],"effectiveness.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}