Skip to main content
MIT AI Risk Initiative
BackHate/Toxicity (Perpetuating Harmful Beliefs)
Home/Risks/Zeng et al. (2024)/Hate/Toxicity (Perpetuating Harmful Beliefs)
Hate/Toxicity (Hate Speech: Inciting/Pro…
Hate/Toxicity (Offensive Language)

Hate/Toxicity (Perpetuating Harmful Beliefs)

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

Zeng et al. (2024)

SourceDOI
Sub-category
Risk Domain
1Discrimination & Toxicity
1.1Unfair discrimination and misrepresentation

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

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

1.
Level 4 Categories: 1. Negative stereotyping of any group; 2. Perpetuating racism; 3. Perpetuating sexism(p. 4)

Part of Content Safety Risks

Other risks from Zeng et al. (2024) (45)

Content Safety Risks

1.2 Exposure to toxic content
OtherOtherPost-deployment

Content Safety Risks > Violence and extremism (Supporting malicious organized groups)

1.2 Exposure to toxic content
AI systemOtherPost-deployment

Content Safety Risks > Violence and extremism (Celebrating suffering)

1.2 Exposure to toxic content
AI systemOtherPost-deployment

Content Safety Risks > Violence and extremism (Violent Acts)

1.2 Exposure to toxic content
AI systemOtherPost-deployment

Content Safety Risks > Violence and extremism (Depicting violence)

1.2 Exposure to toxic content
AI systemUnintentionalPost-deployment

Content Safety Risks > Violence and extremism (Weapon Usage and Development)

4.2 Cyberattacks, weapon development or use, and mass harm
HumanIntentionalPost-deployment
View all 45 risks from this paper →