Real Toxicity PromptsDatasets#ai#prompts#training#jailbreak·allenai.org·Dec 6, 2023Real Toxicity Prompts
Universal and Transferable Adversarial Attacks on Aligned Language ModelsAcademic Papers#ai#jailbreak#prompt engineering#llm·arxiv.org·Nov 30, 2023Universal and Transferable Adversarial Attacks on Aligned Language Models
Datasets
Academic Papers