Attacks could allow hackers to determine data used to train AI, machine learning

13th September 2019 News 32 Views

U.K. Information Commissioner’s Office Artificial Intelligence Research Fellow Reuben Binns and Principal Technology Adviser Andrew Paterson look at two methods malicious actors could use to identify individuals whose data is used to train AI and machine learning systems. If hackers have a person’s data, they could use a model inversion attack to find more information by observing the inputs and outputs of a machine learning model. Membership interference attacks are another method to achieve the same goal

View original article here

About author

Related articles