Work

From Liberty to 1984: A Methodology for Systematically Deteriorating LLM Outputs through Habituation Tendencies

Year: 2024

Type: conference-paper

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

DOI: 10.1109/trustcom63139.2024.00228

Authors: Dong Zhang, Zhiyuan Hu, Huijun Chen, Guangming Liu, YinFeng Zheng, Jinghui Lu

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4409156307

FWCI:

Cites: 13

Cited by:

Related to: 10