Incident 552: Bing Chat Solved CAPTCHAs with Image Analysis Feature Despite Safeguards

Description: Microsoft was reported by a Twitter user for deploying image analysis feature capable of solving CAPTCHAs for its GPT-based chatbot despite it being safeguarded against solving them for users.

Tools

New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History
Alleged: OpenAI developed an AI system deployed by , which harmed Microsoft.

Incident Stats

Incident ID
552
Report Count
1
Incident Date
2023-06-22
Editors
Khoa Lam

Incident Reports

Reports Timeline

Tweet: @sayashk

Tweet: @sayashk

twitter.com

Tweet: @sayashk
twitter.com · 2023

I'd heard that GPT-4's image analysis feature wasn't available to the public because it could be used to break Captcha.

Turns out it's true: The new Bing can break captcha, despite saying it won't:

Getting many comments about whether this i…

Variants

A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.