Skip to main content
This is a research prototype. The data and analyses are preliminary and not yet validated — we'd welcome your .
MIT AI Risk Initiative
BackMalicious Use
Dissemination of dangerous information
Influence operations

Malicious Use

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger et al. (2023)

SourceDOI
Category

"AI systems reducing the costs and facilitating activities of actors trying to cause harm (e.g. fraud, weapons)"(p. 14)

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 (4)

Influence operations

"Facilitating large-scale disinformation campaigns and targeted manipulation of public opinion"

4.1 Disinformation, surveillance, and influence at scale
HumanIntentionalPost-deployment

Fraud

"Facilitating fraud, cheating, forgery, and impersonation scams"

4.3 Fraud, scams, and targeted manipulation
IntentionalPost-deployment

Defamation

"Facilitating slander, defamation, or false accusations"

4.1 Disinformation, surveillance, and influence at scale
HumanIntentionalPost-deployment

Security threats

"Facilitating the conduct of cyber attacks, weapon development, and security breaches"

4.2 Cyberattacks, weapon development or use, and mass harm
HumanIntentionalPost-deployment

Other risks from Weidinger et al. (2023) (26)

Representation & Toxicity Harms

1.0 Discrimination & Toxicity
AI systemUnintentionalPost-deployment

Representation & Toxicity Harms > Unfair representation

1.1 Unfair discrimination and misrepresentation
AI systemUnintentionalPost-deployment

Representation & Toxicity Harms > Unfair capability distribution

1.3 Unequal performance across groups
AI systemUnintentionalPost-deployment

Representation & Toxicity Harms > Toxic content

1.2 Exposure to toxic content
AI systemUnintentionalPost-deployment

Misinformation Harms

3.0 Misinformation
AI systemOtherPost-deployment

Misinformation Harms > Propagating misconceptions/ false beliefs

3.1 False or misleading information
AI systemOtherPost-deployment
View all 26 risks from this paper →