{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:40:07Z","timestamp":1750747207889,"version":"3.41.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100011332","name":"University of Chinese Academy of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011332","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,5]]},"DOI":"10.1109\/cscwd64889.2025.11033427","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:24:40Z","timestamp":1750699480000},"page":"1838-1843","source":"Crossref","is-referenced-by-count":0,"title":["A Jailbreak Prompt Detector Based on Selective Perturbation and Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Yanshu","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitian","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.443"},{"key":"ref2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"journal-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref3"},{"journal-title":"Baseline defenses for adversarial attacks against aligned language models","year":"2023","author":"Jain","key":"ref4"},{"journal-title":"Llm self defense: By self examination, llms know they are being tricked","year":"2023","author":"Phute","key":"ref5"},{"journal-title":"Foundational challenges in assuring alignment and safety of large language models","year":"2024","author":"Anwar","key":"ref6"},{"journal-title":"Detecting language model attacks with perplexity","year":"2023","author":"Alon","key":"ref7"},{"journal-title":"Token-level adversarial prompt detection based on perplexity measures and contextual information","year":"2023","author":"Hu","key":"ref8"},{"journal-title":"Smoothllm: Defending large language models against jailbreaking attacks","year":"2023","author":"Robey","key":"ref9"},{"journal-title":"Defending large language models against jailbreak attacks via semantic smoothing","year":"2024","author":"Ji","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.30"},{"journal-title":"Robust safety classifier for large language models: Adversarial prompt shield","year":"2023","author":"Kim","key":"ref12"},{"journal-title":"Certifying llm safety against adversarial prompting","year":"2023","author":"Kumar","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31638"},{"volume-title":"Perspective api","year":"2024","key":"ref15"},{"volume-title":"Moderation-openai api","year":"2024","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.09.013"},{"issue":"140","key":"ref18","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref19","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"journal-title":"Universal and transferable adversarial attacks on aligned language models","year":"2023","author":"Zou","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670388"},{"journal-title":"Alpacaeval: An automatic evaluator of instruction-following models","year":"2023","author":"Li","key":"ref22"},{"issue":"364","key":"ref23","author":"Liu","year":"2019","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"journal-title":"Fine-tuned deberta-v3 for prompt injection detection","year":"2023","key":"ref25"},{"journal-title":"Llama guard: Llm-based input-output safeguard for human-ai conversations","year":"2023","author":"Inan","key":"ref26"},{"volume-title":"Azureai content safety documentation","year":"2024","key":"ref27"}],"event":{"name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2025,5,5]]},"location":"Compiegne, France","end":{"date-parts":[[2025,5,7]]}},"container-title":["2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11033175\/11033221\/11033427.pdf?arnumber=11033427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:05:22Z","timestamp":1750745122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cscwd64889.2025.11033427","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]}}}