Incidente 552: translated-es-Bing Chat Solved CAPTCHAs with Image Analysis Feature Despite Safeguards
Descripción: translated-es-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.
Entidades
Ver todas las entidadesEstadísticas de incidentes
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.
- Privacy & Security
Entity
Which, if any, entity is presented as the main cause of the risk
AI
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
Unintentional
Informes del Incidente
Cronología de Informes
Escuché que la función de análisis de imágenes de GPT-4 no estaba disponible para el público porque podría usarse para romper Captcha.
Resulta que es cierto: el nuevo Bing puede romper el captcha, a pesar de decir que no lo hará:
Recibiendo…
Variantes
Una "Variante" es un incidente de IA similar a un caso conocido—tiene los mismos causantes, daños y sistema de IA. En lugar de enumerarlo por separado, lo agrupamos bajo el primer incidente informado. A diferencia de otros incidentes, las variantes no necesitan haber sido informadas fuera de la AIID. Obtenga más información del trabajo de investigación.
¿Has visto algo similar?
Incidentes Similares
Did our AI mess up? Flag the unrelated incidents
Incidentes Similares
Did our AI mess up? Flag the unrelated incidents