BackOperational misuses (Automated decision-making)
Operational misuses (Automated decision-making)
Risk Domain
Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and unfair representation of those groups.
Entity: Who or what caused the harm
Intent: Whether the harm was intentional or accidental
Timing: Whether the risk is pre- or post-deployment
Supporting Evidence (1)
1.
Level 4 Categories: 1. Financial eligibility/creditworthiness; 2. Criminal justice/predictive policing; 3. Adversely affecting legal rights; 4. Employment; 5. Social scoring; 6. Housing eligibility; 7. Education eligibility; 8. Migration eligibility; 9. Insurance eligibility; 10. Profiling(p. 4)
Other risks from Zeng et al. (2024) (45)
Content Safety Risks
1.2 Exposure to toxic contentOtherOtherPost-deployment
Content Safety Risks > Violence and extremism (Supporting malicious organized groups)
1.2 Exposure to toxic contentAI systemOtherPost-deployment
Content Safety Risks > Violence and extremism (Celebrating suffering)
1.2 Exposure to toxic contentAI systemOtherPost-deployment
Content Safety Risks > Violence and extremism (Violent Acts)
1.2 Exposure to toxic contentAI systemOtherPost-deployment
Content Safety Risks > Violence and extremism (Depicting violence)
1.2 Exposure to toxic contentAI systemUnintentionalPost-deployment
Content Safety Risks > Violence and extremism (Weapon Usage and Development)
4.2 Cyberattacks, weapon development or use, and mass harmHumanIntentionalPost-deployment