{"id":"https://openalex.org/W4415025828","doi":"https://doi.org/10.1109/tps-isa67132.2025.00036","title":"Learning from Literature: A Retraining-Free Framework for LLM Jailbreak Defense via NLP-Based Adversarial Literature Analysis","display_name":"Learning from Literature: A Retraining-Free Framework for LLM Jailbreak Defense via NLP-Based Adversarial Literature Analysis","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4415025828","doi":"https://doi.org/10.1109/tps-isa67132.2025.00036"},"language":"en","primary_location":{"id":"doi:10.1109/tps-isa67132.2025.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tps-isa67132.2025.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)","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/2505.01315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116054033","display_name":"Sheikh Samit Muhaimin","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheikh Samit Muhaimin","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022042508","display_name":"Spyridon Mastorakis","orcid":"https://orcid.org/0000-0002-8498-4718"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spyridon Mastorakis","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23905707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"270","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5841000080108643,"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/T10028","display_name":"Topic Modeling","score":0.5841000080108643,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9014999866485596},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8898000121116638},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.7736999988555908},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5748000144958496},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4602999985218048},{"id":"https://openalex.org/keywords/resistance","display_name":"Resistance (ecology)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.426800012588501}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9014999866485596},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8898000121116638},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.7736999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339000105857849},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101000070571899},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C57473165","wikidata":"https://www.wikidata.org/wiki/Q7315604","display_name":"Resistance (ecology)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tps-isa67132.2025.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tps-isa67132.2025.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.01315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01315","pdf_url":"https://arxiv.org/pdf/2505.01315","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":"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":"pmh:doi:10.48550/arxiv.2505.01315","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2505.01315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.01315","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":"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:2505.01315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01315","pdf_url":"https://arxiv.org/pdf/2505.01315","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415025828.pdf","grobid_xml":"https://content.openalex.org/works/W4415025828.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W4393116578","https://openalex.org/W4413169625","https://openalex.org/W4405181600","https://openalex.org/W4391992626","https://openalex.org/W3193514658","https://openalex.org/W3033185959","https://openalex.org/W2609923048","https://openalex.org/W2101234009","https://openalex.org/W4392941823","https://openalex.org/W4405219474","https://openalex.org/W3159085860","https://openalex.org/W2964008919","https://openalex.org/W4399167765","https://openalex.org/W3164702673","https://openalex.org/W4402683892","https://openalex.org/W3176580738","https://openalex.org/W4388488609","https://openalex.org/W4391724817","https://openalex.org/W4386301836","https://openalex.org/W4402670423"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"surge":[1],"in":[2],"adoption":[3],"of":[4,69,136,162,180,189],"Large":[5],"Language":[6,108],"Models":[7],"(LLMs)":[8],"have":[9],"made":[10],"them":[11],"vulnerable":[12],"to":[13,49,84,170,173,209],"sophisticated":[14],"adversarial":[15,58,81,139,190],"attacks,":[16],"manipulative":[17,155],"prompts,":[18,151],"and":[19,35,53,79,92,101,118,127,154,183,212],"encoded":[20,119,150],"malicious":[21,56,128,152,174],"inputs.":[22],"Existing":[23],"countermeasures":[24],"often":[25],"require":[26],"retraining":[27,62],"models,":[28],"a":[29,42,159,177,205],"process":[30],"that":[31,46,77,98,144],"is":[32],"computationally":[33],"expensive":[34],"impractical":[36],"for":[37],"deployment.":[38],"This":[39],"paper":[40],"introduces":[41],"novel":[43],"defense":[44,90],"framework":[45,67,165,196],"enables":[47,167],"LLMs":[48,137],"autonomously":[50],"detect,":[51],"filter,":[52],"fend":[54],"off":[55],"or":[57,63],"inputs":[59,104],"without":[60],"requiring":[61],"fine-tuning.":[64],"The":[65,164,195],"proposed":[66],"consists":[68],"two":[70],"core":[71],"components:":[72],"(1)":[73],"A":[74,94],"summarization":[75],"module":[76,97],"processes":[78],"summarizes":[80],"research":[82,191],"literature":[83,192],"provide":[85],"the":[86,134,168],"LLM":[87,199,217],"with":[88,158,176],"context-aware":[89],"knowledge":[91],"(2)":[93],"prompt":[95,129],"filtering":[96],"detects,":[99],"decodes,":[100],"classifies":[102],"harmful":[103],"through":[105],"advanced":[106],"Natural":[107],"Processing":[109],"(NLP)":[110],"techniques,":[111],"such":[112],"as":[113,193,204],"zero-shot":[114],"classification,":[115],"keyword":[116],"analysis,":[117,130],"content":[120],"detection.":[121],"By":[122],"combining":[123],"text":[124],"extraction,":[125],"summarization,":[126],"this":[131,145],"approach":[132,147],"enhances":[133],"robustness":[135],"against":[138],"misuse.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"integrated":[146],"successfully":[148],"identifies":[149],"patterns,":[153],"language":[156],"structures":[157],"success":[160],"rate":[161],"98.7%.":[163],"also":[166],"model":[169],"respond":[171],"appropriately":[172],"prompts":[175],"higher":[178],"percentage":[179],"jailbreak":[181],"resistance":[182],"refusal":[184],"rate,":[185],"using":[186],"minimal":[187],"quantity":[188],"context.":[194],"significantly":[197],"reduces":[198],"Attack":[200],"Success":[201],"Rate":[202],"(ASR)":[203],"lightweight,":[206],"efficient":[207],"alternative":[208],"retraining-based":[210],"time":[211],"resource-consuming":[213],"defenses,":[214],"while":[215],"upholding":[216],"response":[218],"quality.":[219]},"counts_by_year":[],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}