ChatGPT: Hacking Memories via Images (Prompt Injection to Persistent Memories)
HTML-код
- Опубликовано: 11 сен 2024
- Details: embracethered....
This was issue was disclosed to OpenAI in May 2024, but seen as a "model safety issue" and not a security vulnerability.
*DISCLAIMER*: Penetration testing and red teaming requires authorization from proper stakeholders. Do not perform unauthorized or illegal activities. This content is for educational purposes to help secure systems and educate users and developers about AI safety threats and mitigations.