Poisoning Attacks Against Machine Learning: Can Machine Learning Be Trustworthy?
Alina Oprea, Anoop Singhal, Apostol Vassilev
Abstract
Many practical applications benefit from machine learning and artificial intelligence technologies, but their security needs to be studied in more depth. We discuss the risk of poisoning attacks against the training stage of machine learning and challenges of defending against them.
Topics & Concepts
Computer scienceTrustworthinessComputer securityArtificial intelligenceAdversarial machine learningMachine learningDeep learningHuman–computer interactionAdversarial Robustness in Machine Learning