Sep 15, 2022Confirmed
GPT-3-Based Twitter Bot Hijacked Using Prompt Injection Attacks
Rogue: Caused harmAI loose in the worldInjectionDERIVED
Approved by person, Oct 11, 2026. How entries are approved
Remoteli.io's GPT-3-based Twitter bot was shown being hijacked by Twitter users who redirected it to repeat or generate any phrases.
What this means for youAt home: a public AI bot can be tricked by strangers into saying things its owner never intended. At work: any customer-facing chatbot needs limits on what it can say and do. In government: this shows why rules for testing public-facing AI matter. If you run a bot, check what it can post or access, and add human review before it publishes.
Sources
- AI Incident Databasehttps://incidentdatabase.ai/cite/352
Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.
Source data license: CC BY-SA 4.0 (database). Report contents keep their own rights; reports.text, submissions, images and videos are excluded from the data license.
rogue:R4
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2004. It has not been edited since it was approved; the hash above would not match if it had. How to verify