New hack uses prompt injection to corrupt Gemini’s long-term memory

Image credit: Cliff Hang via Pixabay. Article by Dan Goodin. Ars Technica – February 11, 2025.

In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google’s Gemini and OpenAI’s ChatGPT are generally good at plugging these security holes, but hackers keep finding new ways to poke through […]

Click here to view original web page at arstechnica.com