{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:19Z","timestamp":1737176839188,"version":"3.33.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825267","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"2376-2383","source":"Crossref","is-referenced-by-count":0,"title":["AutoRed: Automated Attack Scenario Generation Framework for Red Teaming of LLMs"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Wang","sequence":"first","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Burnaby,Canada"}]},{"given":"Mohammad A.","family":"Tayebi","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Burnaby,Canada"}]}],"member":"263","reference":[{"volume":"1996","volume-title":"Sixth message understanding conference (MUC-6).: proceedings of a conference held in Columbia","key":"ref1"},{"key":"ref2","first-page":"267","article-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","volume-title":"28th USENIX security symposium (USENIX security 19)","author":"Carlini"},{"key":"ref3","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini"},{"article-title":"Safe rlhf: Safe reinforcement learning from human feedback","year":"2023","author":"Dai","key":"ref4"},{"article-title":"Cybersecurity-attack and defense strategies: Infrastructure security with red team and blue team tactics","year":"2018","author":"Diogenes","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623985"},{"journal-title":"Curiosity-driven red-teaming for large language models","year":"2024","author":"Hong","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"ref9","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Can llms keep a secret? testing privacy implications of language models via contextual integrity theory","year":"2023","author":"Mireshghallah","key":"ref10"},{"volume-title":"Openai: Gpt-3 and beyond","key":"ref11"},{"key":"ref12","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"},{"key":"ref13","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"},{"volume-title":"Top 10 for Large Language Model Applications","key":"ref14"},{"article-title":"Can sensitive information be deleted from llms? objectives for defending against extraction attacks","year":"2023","author":"Patil","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"journal-title":"Fine-tuned deberta-v3 for prompt injection detection","key":"ref17"},{"key":"ref18","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"140","key":"ref19","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"},{"article-title":"Is reinforcement learning (not) for natural language processing?: Benchmarks, baselines, and building blocks for natural language policy optimization","year":"2022","author":"Ramamurthy","key":"ref20"},{"journal-title":"NLPGym \u2013 a toolkit for evaluating RL agents on natural language processing tasks","year":"2020","author":"Ramamurthy","key":"ref21"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"article-title":"Beyond memorization: Violating privacy via inference with large language models","year":"2023","author":"Staab","key":"ref24"},{"journal-title":"Tensor Trust: Interpretable prompt injection attacks from an online game","year":"2023","author":"Toyer","key":"ref25"},{"volume-title":"Leaderboard","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Finetuned language models are zero-shot learners","year":"2021","author":"Wei","key":"ref28"},{"article-title":"Bloomberggpt: A large language model for finance","year":"2023","author":"Wu","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4489826"},{"article-title":"React: Synergizing reasoning and acting in language models","year":"2022","author":"Yao","key":"ref31"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825267.pdf?arnumber=10825267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:46:03Z","timestamp":1737099963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825267\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825267","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}