Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse
Discover
Submit
  • Welcome to the AIID
  • Discover Incidents
  • Spatial View
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Submit Incident Reports
  • Submission Leaderboard
  • Blog
  • AI News Digest
  • Risk Checklists
  • Random Incident
  • Sign Up
Collapse

Incident 473: Bing Chat's Initial Prompts Revealed by Early Testers Through Prompt Injection

Description: Early testers of Bing Chat successfully used prompt injection to reveal its built-in initial instructions, which contains a list of statements governing ChatGPT's interaction with users.

Tools

New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History

Entities

View all entities
Alleged: OpenAI developed an AI system deployed by , which harmed Microsoft.

Incident Stats

Incident ID
473
Report Count
1
Incident Date
2023-02-08
Editors
Khoa Lam
Applied Taxonomies
MIT

MIT Taxonomy Classifications

Machine-Classified
Taxonomy Details

Risk Subdomain

A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
 

2.2. AI system security vulnerabilities and attacks

Risk Domain

The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
 
  1. Privacy & Security

Entity

Which, if any, entity is presented as the main cause of the risk
 

Human

Timing

The stage in the AI lifecycle at which the risk is presented as occurring
 

Post-deployment

Intent

Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
 

Intentional

Incident Reports

Reports Timeline

Incident OccurrenceAI-powered Bing Chat spills its secrets via prompt injection attack [Updated]
AI-powered Bing Chat spills its secrets via prompt injection attack [Updated]

AI-powered Bing Chat spills its secrets via prompt injection attack [Updated]

arstechnica.com

AI-powered Bing Chat spills its secrets via prompt injection attack [Updated]
arstechnica.com · 2023

On Tuesday, Microsoft revealed a "New Bing" search engine and conversational bot powered by ChatGPT-like technology from OpenAI. On Wednesday, a Stanford University student named Kevin Liu used a prompt injection attack to discover Bing Cha…

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.

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Biased Sentiment Analysis

Oct 2017 · 7 reports
Inappropriate Gmail Smart Reply Suggestions

Inappropriate Gmail Smart Reply Suggestions

Nov 2015 · 22 reports
High-Toxicity Assessed on Text Involving Women and Minority Groups

High-Toxicity Assessed on Text Involving Women and Minority Groups

Feb 2017 · 9 reports
Previous IncidentNext Incident

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Biased Sentiment Analysis

Oct 2017 · 7 reports
Inappropriate Gmail Smart Reply Suggestions

Inappropriate Gmail Smart Reply Suggestions

Nov 2015 · 22 reports
High-Toxicity Assessed on Text Involving Women and Minority Groups

High-Toxicity Assessed on Text Involving Women and Minority Groups

Feb 2017 · 9 reports

Research

  • Defining an “AI Incident”
  • Defining an “AI Incident Response”
  • Database Roadmap
  • Related Work
  • Download Complete Database

Project and Community

  • About
  • Contact and Follow
  • Apps and Summaries
  • Editor’s Guide

Incidents

  • All Incidents in List Form
  • Flagged Incidents
  • Submission Queue
  • Classifications View
  • Taxonomies

2023 - AI Incident Database

  • Terms of use
  • Privacy Policy
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • f28fa7c