Work

DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy

Year: 2025

Type: conference-paper

Source: International Conference on Computer Supported Cooperative Work in Design (CSCWD)

DOI: 10.1109/cscwd64889.2025.11033375

Authors: Xuehai Tang, Xikang Yang, Zhongjiang Yao, Jie Wen, Xi Zhou, Jizhong Han, Songlin Hu

Institutions: Chinese Academy of Sciences, Institute of Information Engineering

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4411551265

FWCI: 2.011

Cites: 19

Cited by: 2

Related to: 10