A simple technique to defend ChatGPT against jailbreak attacks
Large language models (LLMs), deep learning-based models trained to generate, summarize, translate and process written text, have attracted considerable attention ...
Tag: jailbreak
Researchers use AI chatbots against themselves to “jailbreak” each other
Computer scientists at Nanyang Technological University Singapore (NTU Singapore) have successfully compromised several artificial intelligence (AI) chatbots, including ChatGPT, Google ...
