{"id":"https://openalex.org/W4415975210","doi":"https://doi.org/10.1109/iccv51701.2025.00266","title":"Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-Based Attacks","display_name":"Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-Based Attacks","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415975210","doi":"https://doi.org/10.1109/iccv51701.2025.00266"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.01308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100388766","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0002-3069-3448"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014544686","display_name":"Yushen Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yushen Zuo","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120286188","display_name":"Yuanjun Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanjun Chai","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088262967","display_name":"Zhendong Liu","orcid":"https://orcid.org/0000-0002-7554-7962"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Liu","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112697148","display_name":"Yicheng Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yicheng Fu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yichun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichun Feng","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kin-Man Lam","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2773","last_page":"2782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9725000262260437,"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":0.9725000262260437,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.698199987411499},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42739999294281006},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41510000824928284},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3555999994277954},{"id":"https://openalex.org/keywords/threat-model","display_name":"Threat model","score":0.3312000036239624},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.311599999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378000020980835},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.698199987411499},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C29825287","wikidata":"https://www.wikidata.org/wiki/Q1427940","display_name":"Warning system","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2779079576","wikidata":"https://www.wikidata.org/wiki/Q17092823","display_name":"Jamming","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.01308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01308","pdf_url":"https://arxiv.org/pdf/2504.01308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2504.01308","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.01308","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.01308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01308","pdf_url":"https://arxiv.org/pdf/2504.01308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1,9],"(VLMs)":[2],"extend":[3],"the":[4,138],"capabilities":[5],"of":[6,103,141],"Large":[7],"Language":[8],"(LLMs)":[10],"by":[11,128],"incorporating":[12],"visual":[13,45,108],"information,":[14],"yet":[15],"they":[16],"remain":[17],"vulnerable":[18],"to":[19,37,66,117],"jailbreak":[20],"attacks,":[21,40,110],"especially":[22],"when":[23],"processing":[24],"noisy":[25],"or":[26],"corrupted":[27],"images.":[28],"Although":[29],"existing":[30],"VLMs":[31,63,129],"adopt":[32],"security":[33,60],"measures":[34],"during":[35],"training":[36,57],"mitigate":[38],"such":[39,70],"vulnerabilities":[41],"associated":[42],"with":[43,85,92,130,146],"noise-augmented":[44,56,93,131],"inputs":[46],"are":[47,64,161],"overlooked.":[48],"In":[49],"this":[50,76],"work,":[51],"we":[52,78,111],"identify":[53],"that":[54,95,137],"missing":[55],"causes":[58],"critical":[59],"gaps:":[61],"many":[62],"susceptible":[65],"even":[67],"simple":[68],"perturbations":[69,120,153],"as":[71],"Gaussian":[72],"noise.":[73],"To":[74],"address":[75],"challenge,":[77],"propose":[79,112],"Robust-VLGuard,":[80],"a":[81],"multimodal":[82],"safety":[83,132],"dataset":[84,158],"aligned":[86],"/":[87],"misaligned":[88],"image-text":[89],"pairs,":[90],"combined":[91],"fine-tuning":[94],"reduces":[96],"attack":[97],"success":[98],"rates":[99],"while":[100],"preserving":[101],"functionality":[102],"VLM.":[104],"For":[105],"stronger":[106],"optimization-based":[107],"perturbation":[109],"DiffPure-VLM,":[113],"leveraging":[114],"diffusion":[115,142],"models":[116],"convert":[118],"adversarial":[119,152],"into":[121],"Gaussian-like":[122],"noise,":[123],"which":[124],"can":[125],"be":[126],"defended":[127],"fine-tuning.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"distribution-shifting":[139],"property":[140],"model":[143],"aligns":[144],"well":[145],"our":[147],"fine-tuned":[148],"VLMs,":[149],"significantly":[150],"mitigating":[151],"across":[154],"varying":[155],"intensities.":[156],"The":[157],"and":[159],"code":[160],"available":[162],"at":[163],"https://github.com/JarvisUSTC/DiffPure-RobustVLM.":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}