Litcius/Paper detail

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Jiashu Xu, Mingyu Ma, Fei Wang, Chaowei Xiao, Muhao Chen

202434 citationsDOIOpen Access PDF

Abstract

Jiashu Xu, Mingyu Ma, Fei Wang, Chaowei Xiao, Muhao Chen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Topics & Concepts

BackdoorComputer scienceComputer securitySoftware Testing and Debugging TechniquesAdversarial Robustness in Machine LearningSecurity and Verification in Computing
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models | Litcius