Work

Deceiving LLM through Compositional Instruction with Hidden Attacks

Year: 2025

Type: article

Source: ACM Transactions on Autonomous and Adaptive Systems

DOI: 10.1145/3717067

Authors: Shuyu Jiang, Xingshu Chen, Rui Tang

Institution: Sichuan University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4407506574

FWCI: 4.123

Cites: 19

Cited by: 10

Related to: 10