MIT AI Risk Repository · Risk Sub-Category · 45.02.11
Ethical Risks (Risks of exacerbating social discrimination and prejudice, and widening the intelligence divide)
Category: Safety risks in AI Applications
On this page 5 sections
Description
"AI can be used to collect and analyze human behaviors, social status, economic status, and individual personalities, labeling and categorizing groups of people to treat them discriminatingly, thus causing systematic and structural social discrimination and prejudice. At the same time, the intelligence divide would be expanded among regions."
From AI Safety Governance Framework (TC2602024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Causal entity
- Human
- Intent
- Intentional
- Timing
- Post-deployment
Subdomain definition: Widespread use of AI increasing social and economic inequalities, such as by automating jobs, reducing the quality of employment, or producing exploitative dependencies between workers and their employers.
Real-world incidents in this subdomain
- Polish Radio Station Replaces Human Hosts with AI-Generated Presenters to Simulate Interviewing Deceased Poet Wisława Szymborska
- Fast Food Chains' AI Chatbots Failed to Assist Job Applicants with Scheduling Interviews
- Kenyan Data Annotators Allegedly Exposed to Graphic Content for OpenAI's AI
- RealPage Algorithm Allegedly Inflates Rents and Reduces Competition in Housing Market
- Amazon Flex Drivers Allegedly Fired via Automated Employee Evaluations
- Kronos Scheduling Algorithm Allegedly Caused Financial Issues for Starbucks Employees
How other frameworks describe this risk
Other entries from TC2602024
- AI's inherent safety risks
- Risks from models and algorithms (Risks of explainability)
- Risks from models and algorithms (Risks of bias and discrimination)
- Risks from models and algorithms (Risks of robustness)
- Risks from models and algorithms (Risks of stealing and tampering)
- Risks from models and algorithms (Risks of unreliable output)
- Risks from models and algorithms (Risks of adversarial attack)
- Risks from data (Risks of illegal collection and use of data)
- Risks from data (Risks of improper content and poisoning in training data)
- Risks from data (Risks of unregulated training data annotation)
- Risks from data (Risks of data leakage)
- Risks from AI systems (Risks of exploitation through defects and backdoors)