data poisoning

plural data poisonings

1. countableuncountablemachine learning; computer security; machine learning; computer securityThe deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model.

   While data sanitization shows promise to defend against data poisoning, it is often impossible to validate every data source [14].

   2019, Simon N. Foley, editor, Data and Applications Security and Privacy XXXIII […] , Springer, →ISBN, page 4

   3 more examples

   Similarly, the Tay chatbot suffered from data poisoning. To mitigate data poisoning, it is important not to let any one group contribute too much data to a model.

   2022, Alfred Z. Spector, Peter Norvig, Chris Wiggins, Jeannette M. Wing, Data Science in Context: Foundations, Challenges, Opportunities, Cambridge University Press, →ISBN, page 148

   Data poisoning is one type of adversarial attack—where a user or group of users submit false data to influence the model toward a particular or incorrect prediction.

   2023, Katharine Jarmul, Practical Data Privacy, O'Reilly, →ISBN

   Some forms of data poisoning are undetectable. Attackers can insert adversarial noise into the training data, altering the training data in a way that is hidden to human observers.

   2023, Paul Scharre, Four Battlegrounds: Power in the Age of Artificial Intelligence, W. W. Norton & Company, →ISBN

   Synonyms: poisoning attack