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

Concepedia

Publication | Open Access

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

DOI Full Paper Access

24

Citations

0

References

2024

Year

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

Unknown Venue

Natural Language ProcessingLarge Language ModelsEngineeringMachine LearningProgram AnalysisAttack ModelAdversarial Machine LearningBackdoor AttacksComputer ScienceLarge Language ModelUniversal VulnerabilitiesLanguage-based SecurityLanguage Processing

No additional data available for this publication yet. Check back later!