Researchers Use AI to Jailbreak ChatGPT, Other LLMs

quot;Tree of Attacks With Pruning" is the latest in a growing string of methods for eliciting unintended behavior from a large language model.

From DAN to Universal Prompts: LLM Jailbreaking

From the headlines: ChatGPT and other AI text-generating risks

Researchers Use AI in New Automated LLM Jailbreaking Method

ChatGPT-Dan-Jailbreak.md · GitHub

Jailbreaking ChatGPT: How AI Chatbot Safeguards Can be Bypassed - Bloomberg

ChatGPT - Wikipedia

Fight AI with AI: Going Beyond ChatGPT - Deep Instinct

I Had a Dream and Generative AI Jailbreaks

Researchers Uncovered a New Flaw in AI Chatbots to Evil

The Impact of ChatGPT on the Federal Workforce

New method reveals how one LLM can be used to jailbreak another

From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy – arXiv Vanity

Jailbreaker: Automated Jailbreak Across Multiple Large Language Model Chatbots – arXiv Vanity

As Online Users Increasingly Jailbreak ChatGPT in Creative Ways, Risks Abound for OpenAI - Artisana