Work

Defending LLMs against jailbreak attacks through representation offset detection

Year: 2026

Type: article

Source: Information Processing & Management

DOI: 10.1016/j.ipm.2026.104662

Authors: Shuo Liu, Xiang Cheng, Zhenzhong Zheng, Sen Su

Institutions: Beijing University of Posts and Telecommunications, State Key Laboratory of Networking and Switching Technology

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: National Natural Science Foundation of China

OpenAlex ID: W7127088984

FWCI:

Cites: 9

Cited by:

Related to: 10