Work

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Year: 2025

Type: conference-paper

Abstract: Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2025.emnlp-main.1248

Authors: Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Institutions: Harbin Institute of Technology, Singapore Management University, National University of Singapore

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Ministry of Education, India, National Science and Technology Major Project, Fundamental Research Funds for the Central Universities

Award: G2656429412

OpenAlex ID: W4416035752

FWCI: 1.907

Cites:

Cited by: 2

Related to: 10