BackToxicity and Abusive Content
Toxicity and Abusive Content
Risk Domain
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 typically refers to rude, harmful, or inappropriate expressions.(p. 2)
Entity— Who or what caused the harm
Intent— Whether the harm was intentional or accidental
Timing— Whether the risk is pre- or post-deployment
Other risks from Deng et al. (2023) (6)
Unfairness and Discrimination
1.1 Unfair discrimination and misrepresentationOtherOtherPost-deployment
Ethics and Morality Issues
7.3 Lack of capability or robustnessAI systemOtherPost-deployment
Controversial Opinions
1.2 Exposure to toxic contentAI systemOtherPost-deployment
Misleading Information
3.1 False or misleading informationAI systemUnintentionalPost-deployment
Privacy and Data Leakage
2.1 Compromise of privacy by leaking or correctly inferring sensitive informationAI systemUnintentionalPre-deployment
Malicious Use and Unleashing AI Agents
4.0 Malicious Actors & MisuseOtherIntentionalPost-deployment