Skip to main content
MIT AI Risk Initiative
BackSex-related crimes
Home/Risks/Vidgen et al. (2024)/Sex-related crimes
Sale, purchase or use of illegal, highly…
Sexual assault (e.g., rape)

Sex-related crimes

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Vidgen et al. (2024)

SourceDOI
Category
Risk Domain
1Discrimination & Toxicity
1.2Exposure to toxic content

AI that exposes users to harmful, abusive, unsafe or inappropriate content. May involve providing advice or encouraging action. Examples of toxic content include hate speech, violence, extremism, illegal acts, or child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

"This category addresses responses that enable, encourage, or endorse the commission of sex-related crimes"(p. 13)

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

Sub-categories (6)

Sexual assault (e.g., rape)

1.2 Exposure to toxic content
Not codedNot codedNot coded

Sexual harassment

1.2 Exposure to toxic content
Not codedNot codedNot coded

Sex trafficking

1.2 Exposure to toxic content
Not codedNot codedNot coded

Prostitution

1.2 Exposure to toxic content
Not codedNot codedNot coded

Intimate-image based abuse

1.2 Exposure to toxic content
Not codedNot codedNot coded

Indecent exposure (i.e. showing sexual body parts or "flashing")

1.2 Exposure to toxic content
Not codedNot codedNot coded

Other risks from Vidgen et al. (2024) (46)

Violent crimes

1.2 Exposure to toxic content
AI systemOtherPost-deployment

Violent crimes > Mass violence

1.2 Exposure to toxic content
Not codedNot codedNot coded

Violent crimes > Murder

1.2 Exposure to toxic content
Not codedNot codedNot coded

Violent crimes > Physical assault against a person

1.2 Exposure to toxic content
Not codedNot codedNot coded

Violent crimes > Violent domestic abuse

1.2 Exposure to toxic content
Not codedNot codedNot coded

Violent crimes > Terror (Terror groups, Terror actors, Terrorist actions)

1.2 Exposure to toxic content
Not codedNot codedNot coded
View all 46 risks from this paper →