{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:49:31Z","timestamp":1772632171928,"version":"3.50.1"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1109\/tps-isa67132.2025.00036","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:15Z","timestamp":1772571015000},"page":"270-281","source":"Crossref","is-referenced-by-count":0,"title":["Learning from Literature: A Retraining-Free Framework for LLM Jailbreak Defense via NLP-Based Adversarial Literature Analysis"],"prefix":"10.1109","author":[{"given":"Sheikh Samit","family":"Muhaimin","sequence":"first","affiliation":[{"name":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spyridon","family":"Mastorakis","sequence":"additional","affiliation":[{"name":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2024.1405114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/info16080688"},{"key":"ref3","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670388"},{"key":"ref5","article-title":"The ethics of interaction: Mitigating security threats in 11 ms","author":"Kumar","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3367792"},{"key":"ref7","article-title":"Breaking down the defenses: A comparative survey of attacks on large language models","author":"Chowdhury","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Learn from model beyond fine-tuning: A survey","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"The ultimate guide to fine-tuning 11 ms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities","author":"Parthasarathy","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Back to basics: Revisiting reinforce style optimization for learning from human feedback in 11 ms","author":"Ahmadian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Harmbench: A standardized evaluation framework for automated red teaming and robust refusal","author":"Mazeika","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Trustworthy llms: A survey and guideline for evaluating large language models\u2019 alignment","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Securing large language models: Threats, vulnerabilities and responsible practices","author":"Abdali","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Vibecheck: Discover and quantify qualitative differences in large language models","author":"Dunlap","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Fine tuning llm for enterprise: Practical guidelines and recommendations","author":"VM","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Efficient adversarial training in 11 ms with continuous attacks","author":"Xhonneux","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Fine-tuning aligned language models compromises safety, even when users do not intend to!","author":"Qi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Understanding 11 ms: A comprehensive overview from training to inference","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Can llms be fooled? investigating vulnerabilities in 11 ms","author":"Abdali","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"A comprehensive overview of large language models (llms) for cyber defences: Opportunities and directions","author":"Hassanin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Is llm-as-a-judge robust? investigating universal adversarial attacks on zero-shot 11 m assessment","author":"Raina","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Alert: A comprehensive benchmark for assessing large language models\u2019 safety through red teaming","author":"Tedeschi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2021.06.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21512\/comtech.v7i4.3746"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/BCD57833.2023.10466289"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxae124"},{"key":"ref29","article-title":"Jailbroken: How does llm safety training fail?","volume":"36","author":"Wei","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"arXiv","article-title":"Jailbreaking proprietary large language models using word substitution cipher","author":"Handa","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref31","article-title":"Chain of attack: a semantic-driven contextual multi-turn attacker for 11 m","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Defending large language models against jailbreak attacks via semantic smoothing","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Prompt obfuscation for large language models","author":"Pape","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","volume-title":"pdfplumber: Plumb a pdf for detailed information about each char, rectangle, line, et cetera - and easily extract text and tables","author":"Singer-Vine","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICACITE51222.2021.9404712"},{"key":"ref36","volume-title":"Natural language processing with Python and spaCy: A practical introduction","author":"Vasiliev","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-ebaa42b7-00d"},{"key":"ref38","volume-title":"pathos: a framework for heterogeneous computing","author":"McKerns","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0975-5_26"},{"key":"ref40","article-title":"Automated evaluation of personalized text generation using large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2102-4_71"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.11"},{"key":"ref43","article-title":"Embedding-based classifiers can detect prompt injection attacks","author":"Ayub","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","first-page":"175","article-title":"Datasets: A community library for natural language processing","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Online and Punta Cana, Dominican Republic: Association for Computational Linguistics","author":"Lhoest","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.132"},{"key":"ref46","volume-title":"Detoxify","author":"Hanu","year":"2020"},{"key":"ref47","volume-title":"Malicious lm prompt detection in python","author":"Mac","year":"2025"},{"issue":"12","key":"ref48","first-page":"40","article-title":"Llama (llm)","volume":"5","author":"Room","year":"2024","journal-title":"algorithms"},{"key":"ref49","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","first-page":"arXiv-2407","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref51","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Allam: Large language models for arabic and english","author":"Bari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"A comparative study of quality evaluation methods for text summarization","author":"Nguyen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Prompt stealing attacks against large language models","author":"Sha","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06647-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24188"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614777"},{"key":"ref60","article-title":"Survey of vulnerabilities in large language models revealed by adversarial attacks","author":"Shayegani","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Prompt injection attack against 11 m -integrated applications","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Trustllm: Trustworthiness in large language models","volume":"abs\/2401.05561","author":"Sun","year":"2024","journal-title":"ArXiv"},{"key":"ref63","volume":"19","author":"Zou","year":"2024","journal-title":"Universal and transferable adversarial attacks on aligned language models, 2023"},{"key":"ref64","article-title":"Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts. arxiv 2023","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Better robustness by more coverage: Adversarial training with mixup augmentation for robust fine-tuning","author":"Si","year":"2020","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Towards resilient and efficient 11 ms: A comparative study of efficiency, performance, and adversarial robustness","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Struq: Defending against prompt injection with structured queries","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Benchmarking and defending against indirect prompt injection attacks on large language models","author":"Yi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Contextaware prompt tuning: Advancing in-context learning with adversarial methods","author":"Blau","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Safe rlhf: Safe reinforcement learning from human feedback","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Llm self defense: By self examination, 1lms know they are being tricked","author":"Phute","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.267"},{"key":"ref74","article-title":"Knowledge sanitization of large language models","author":"Ishibashi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Casper: Prompt sanitization for protecting user privacy in web-based large language models","author":"Chong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Automated summarization of multiple document abstracts and contents using large language models","author":"Langston","year":"2024","journal-title":"Authorea Preprints"}],"event":{"name":"2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)","location":"Pittsburgh, PA, USA","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 IEEE 7th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410113\/11410157\/11410405.pdf?arnumber=11410405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T06:54:29Z","timestamp":1772607269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tps-isa67132.2025.00036","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}