Work

CVshield: Interpretable Black-Box Adversarial Defense for LLMs via CoT Guided Semantic Verification

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

DOI: 10.1109/trustcom66490.2025.00079

Authors: Wenjing Hu, Weiwei Qi, Yanlu Li, Xinzhe Huang

Institutions: Nanjing University of Science and Technology, Zhejiang University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W7127077355

FWCI:

Cites: 18

Cited by:

Related to: 10