WormGPT

June 19, 2011 - WormGPT, a malicious artificial intelligence (AI) tool, is making a comeback in a new form that no longer relies on self-built models, but instead "hijacks" legitimate large language models (LLMs) to generate malicious content. Research by cybersecurity firm Cato Networks shows that criminal groups are "jailbreaking" models such as xAI's Grok and Mistral AI's Mixtral by tampering with their system prompts to bypass security restrictions and generate phishing emails, Malicious Foot...