Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
Zhexin Zhang, Junxiao Yang, Pei Ke, Fei Mi, Hongning Wang, Minlie Huang
Topics & Concepts
Computer sciencePrioritizationComputer securityRisk analysis (engineering)Process managementEngineeringBusinessInformation and Cyber SecurityAdversarial Robustness in Machine LearningHate Speech and Cyberbullying Detection