{"id":"https://openalex.org/W7124140290","doi":"https://doi.org/10.1109/icpads67057.2025.11323025","title":"SLAG: A Sensitive Layer Activation-Guided Jailbreak Attack on Vision-Language Models","display_name":"SLAG: A Sensitive Layer Activation-Guided Jailbreak Attack on Vision-Language Models","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124140290","doi":"https://doi.org/10.1109/icpads67057.2025.11323025"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085833905","display_name":"J. He","orcid":"https://orcid.org/0000-0001-6934-5080"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing He","raw_affiliation_strings":["School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091767712","display_name":"Yujie Wang","orcid":"https://orcid.org/0009-0004-6021-8412"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Wang","raw_affiliation_strings":["School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123044704","display_name":"Yisheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Li","raw_affiliation_strings":["Nanjing University,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016645765","display_name":"Zhichao Lian","orcid":"https://orcid.org/0000-0002-6643-8975"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Lian","raw_affiliation_strings":["School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62854837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.979200005531311,"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":0.979200005531311,"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":0.0026000000070780516,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.002199999988079071,"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/layer","display_name":"Layer (electronics)","score":0.723800003528595},{"id":"https://openalex.org/keywords/application-layer","display_name":"Application layer","score":0.36559998989105225},{"id":"https://openalex.org/keywords/slag","display_name":"Slag (welding)","score":0.2542000114917755},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.22910000383853912},{"id":"https://openalex.org/keywords/network-layer","display_name":"Network layer","score":0.22110000252723694}],"concepts":[{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.723800003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4221999943256378},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.39480000734329224},{"id":"https://openalex.org/C190793597","wikidata":"https://www.wikidata.org/wiki/Q189768","display_name":"Application layer","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C159048435","wikidata":"https://www.wikidata.org/wiki/Q17105783","display_name":"Slag (welding)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.22910000383853912},{"id":"https://openalex.org/C117468950","wikidata":"https://www.wikidata.org/wiki/Q208074","display_name":"Network layer","level":3,"score":0.22110000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21870000660419464},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2168000042438507},{"id":"https://openalex.org/C62960913","wikidata":"https://www.wikidata.org/wiki/Q1809389","display_name":"Layer by layer","level":3,"score":0.20679999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6159808039665222,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4393157467","https://openalex.org/W4403791397","https://openalex.org/W4409348010"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"SLAG,":[2],"a":[3,30,44,65],"Sensitive":[4],"Layer":[5,61],"ActivationGuided":[6],"jailbreak":[7],"attack":[8],"for":[9],"Large":[10],"Vision-Language":[11],"Models":[12],"(LVLMs).":[13],"SLAG":[14,42],"identifies":[15],"safety-sensitive":[16],"layers":[17,68],"whose":[18],"activations":[19],"differ":[20],"between":[21],"harmful":[22,35],"and":[23,26,57],"benign":[24],"inputs,":[25],"perturbs":[27],"images":[28],"using":[29],"dual-objective":[31],"loss":[32],"to":[33,75],"enhance":[34],"generation":[36],"while":[37],"suppressing":[38],"refusals.":[39],"On":[40],"MiniGPT-4,":[41],"achieves":[43],"95.0%":[45],"Attack":[46],"Success":[47],"Rate":[48],"with":[49],"only":[50],"2000":[51],"steps,":[52],"outperforming":[53],"existing":[54],"image-only":[55],"attacks":[56],"approaching":[58],"multimodal":[59],"methods.":[60],"analysis":[62],"shows":[63],"that":[64],"few":[66],"mid-to-late":[67],"suffice,":[69],"revealing":[70],"multiple":[71],"activation":[72],"pathways":[73],"linked":[74],"safety":[76],"failures.":[77]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-15T00:00:00"}
