Jun 1, 2024Confirmed
Researchers report ChatGPT 4 and 4o can be tricked into leaking users' personal data via prompt injection
AI loose in the worldDERIVED
Approved by person, Oct 11, 2026. How entries are approved
A June 2024 arXiv paper reports that ChatGPT 4 and 4o are open to a prompt injection attack that lets an attacker pull out users' personal data. The authors say the flaw is made worse by ChatGPT's memory feature. The paper includes proofs of concept and a responsible disclosure section.
What this means for youText from a web page or document can carry hidden instructions that an AI chatbot may follow. Be careful about pasting untrusted content into a chatbot, and consider turning off memory if you share personal details with it.
Sources
- arXivhttps://arxiv.org/html/2406.00199v2
Incident records from the AI Agent Incident Database by sipi.bot (https://sipi.bot/incidents/), licensed CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Source data license: CC BY 4.0. Attribution to sipi.bot is required.
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2384. It has not been edited since it was approved; the hash above would not match if it had. How to verify