Get the latest tech news
New hack uses prompt injection to corrupt Gemini’s long-term memory
There’s yet another way to inject malicious prompts into chatbots.
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. The result of Rehberger’s attack is the permanent planting of long-term memories that will be present in all future sessions, opening the potential for the chatbot to act on false information or instructions in perpetuity. Gemini has similarly erected guardrails around the ability to automatically make changes to a user’s long-term conversation memory, a feature Google, OpenAI, and other AI providers have unrolled in recent months.
Or read this on ArsTechnica
