Mitigating adversarial manipulation in LLMs: a prompt-based approach to counter Jailbreak attacks (Prompt-G)
缓解LLM中的对抗性操纵：一种基于提示的方法来对抗越狱攻击（Prompt-G）
期刊:PeerJ Computer Science
影响因子:2.5
doi:10.7717/peerj-cs.2374
Pingua, Bhagyajit; Murmu, Deepak; Kandpal, Meenakshi; Rautaray, Jyotirmayee; Mishra, Pranati; Barik, Rabindra Kumar; Saikia, Manob Jyoti
