Incidente 83: Los filtros de spam de IA supuestamente bloquean correos electrónicos legítimos basándose en la detección sesgada de palabras clave.
Descripción: AlgorithmWatch probó algoritmos de filtrado de spam en Gmail, Yahoo, Outlook, GMX y LaPoste. Sus hallazgos indicaron que el filtro de spam de Microsoft Outlook marcaba correos electrónicos basándose en palabras clave específicas que generaban sesgos raciales y de contenido, bloqueando comunicaciones legítimas. Se descubrió que los correos electrónicos que mencionaban a Nigeria o contenían ciertos términos financieros y de salud sexual se marcaban como spam de forma desproporcionada.
Entidades
Ver todas las entidadesAlleged: Yahoo , LaPoste , GMX , Microsoft y Google developed an AI system deployed by Yahoo , Outlook , LaPoste , GMX y Gmail, which harmed Yahoo! Mail users , Microsoft Outlook users , LaPoste users , GMX users y Gmail Users.
Sistemas de IA presuntamente implicados: Yahoo! Mail's spam filter , SpamAssassin , Microsoft Outlook's spam filter , LaPoste Mail's spam filter , GMX Mail's spam filter y Gmail's spam filter
Clasificaciones de la Taxonomía CSETv1
Detalles de la TaxonomíaIncident Number
The number of the incident in the AI Incident Database.
83
Clasificaciones de la Taxonomía CSETv0
Detalles de la TaxonomíaProblem Nature
Indicates which, if any, of the following types of AI failure describe the incident: "Specification," i.e. the system's behavior did not align with the true intentions of its designer, operator, etc; "Robustness," i.e. the system operated unsafely because of features or changes in its environment, or in the inputs the system received; "Assurance," i.e. the system could not be adequately monitored or controlled during operation.
Specification, Robustness
Physical System
Where relevant, indicates whether the AI system(s) was embedded into or tightly associated with specific types of hardware.
Software only
Level of Autonomy
The degree to which the AI system(s) functions independently from human intervention. "High" means there is no human involved in the system action execution; "Medium" means the system generates a decision and a human oversees the resulting action; "low" means the system generates decision-support output and a human makes a decision and executes an action.
Unclear/unknown
Nature of End User
"Expert" if users with special training or technical expertise were the ones meant to benefit from the AI system(s)’ operation; "Amateur" if the AI systems were primarily meant to benefit the general public or untrained users.
Amateur
Public Sector Deployment
"Yes" if the AI system(s) involved in the accident were being used by the public sector or for the administration of public goods (for example, public transportation). "No" if the system(s) were being used in the private sector or for commercial purposes (for example, a ride-sharing company), on the other.
No
Data Inputs
A brief description of the data that the AI system(s) used or were trained on.
inbound emails
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
1.1. Unfair discrimination and misrepresentation
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.
- Discrimination and Toxicity
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
Un experimento revela que Microsoft Outlook marca los mensajes como spam basándose en una sola palabra, como "Nigeria". Los filtros de spam en gran parte no están auditados y podrían discriminar injustamente.
En un experimento, AlgorithmWat…
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