Information & Safety Harms
AI systems that memorize and leak sensitive personal data or infer private information about individuals without their consent. Unexpected or unauthorized sharing of data and information can compromise user expectation of privacy, assist identity theft, or cause loss of confidential intellectual property.
"AI systems leaking, reproducing, generating or inferring sensitive, private, or hazardous information"(p. 14)
Sub-categories (2)
Privacy infringement
"Leaking, generating, or correctly inferring private and personal information about individuals"
2.1 Compromise of privacy by leaking or correctly inferring sensitive informationDissemination of dangerous information
"Leaking, generating or correctly inferring hazardous or sensitive information that could pose a security threat"
2.1 Compromise of privacy by leaking or correctly inferring sensitive informationOther risks from Weidinger et al. (2023) (26)
Representation & Toxicity Harms
1.0 Discrimination & ToxicityRepresentation & Toxicity Harms > Unfair representation
1.1 Unfair discrimination and misrepresentationRepresentation & Toxicity Harms > Unfair capability distribution
1.3 Unequal performance across groupsRepresentation & Toxicity Harms > Toxic content
1.2 Exposure to toxic contentMisinformation Harms
3.0 MisinformationMisinformation Harms > Propagating misconceptions/ false beliefs
3.1 False or misleading information