We had previously suspected several Chinese and North Korean APTs utilize LLMs for generating scripting-language-based payload, but it looks like they were doing much more than that - with Gemini of all things.
https://cloud.google.com/blog/topics/threat-intelligence/adversarial-misuse-generative-ai/
=> View attached media | View attached media
=> More informations about this toot | More toots from still@infosec.exchange
text/geminiThis content has been proxied by September (3851b).