Concepedia

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning

Shuai Zhao, Meihuizi Jia, Anh Tuan Luu, Fengjun Pan, Jinming Wen

2024 · 28 citations · 0 references

Open access

Concepts

ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningNatural Language ProcessingLanguage ModelingLanguage ModelsSoftware Vulnerability DiscoveryAdversarial Question AnsweringAdversarial RobustnessBackdoor TechniquesIn-context LearningLarge Language Models