QuestionQ47Verified/AI Governance and RiskCopy linkReport a problemAsk AstroTutorSave questionWhich of the following is the MOST relevant control for preventing data and model poisoning?AUse of data from trusted sourcesBData maskingCData anonymizationDEnsuring model outcomes are observableShow AnswerAnswerExplanationData and model poisoning is best prevented by using data from trusted, validated sources, which reduces the chance that malicious or manipulated data is introduced into training data or model inputs.Show comments0Show commentsCommunity DiscussionNo comments yet. Be the first to start the discussion!
Community Discussion