Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models

Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models Jiahui Li author Yongchang Hao author Haoyu Xu author Xing Wang author Yu Hong author 2025-01 text Proceedings of the 31st International Conference on Computational Linguistics Owen Rambow editor Leo Wanner editor Marianna Apidianaki editor Hend Al-Khalifa editor Barbara Di Eugenio editor Steven Schockaert editor Association for Computational Linguistics Abu Dhabi, UAE conference publication li-etal-2025-exploiting https://aclanthology.org/2025.coling-main.305/ 2025-01 4535 4547