Work

Semantic and Precise Trigger Inversion: Detecting Backdoored Language Models

Year: 2025

Type: article

Source: IEEE Transactions on Information Forensics and Security

DOI: 10.1109/tifs.2025.3594037

Authors: Chunlong Xie, Jialing He, Ying Yang, Shangwei Guo, Tianwei Zhang, Tao Xiang

Institutions: Chongqing University, Agency for Science, Technology and Research, Institute of High Performance Computing, Nanyang Technological University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funders: National Natural Science Foundation of China, Chongqing Municipal Development and Reform Commission

Awards: G1546930127, G217923984, G3550020321, G8711352089

OpenAlex ID: W4412748185

FWCI: 1.632

Cites: 45

Cited by: 4

Related to: 10