July 8, 2019
Previous Next

Protecting image classification in artificial intelligence

Oak Ridge Institute for Science and Education

To address vulnerability concerns in image classification, a new subfield of machine learning has emerged called adversarial machine learning, which focuses on the security of machine learning algorithms. Thomas Hogan, a doctoral student of mathematics at UC Davis, spent his summer investigating this new area of research during the National Science Foundation’s Mathematical Sciences Graduate Internship Program. During his internship, Hogan was stationed in the Computational Engineering Division at LLNL. Under the mentorship of Bhavya Kailkhura and Ryan Goldhahn, Hogan attempted to find universal adversarial perturbations that would attempt to fool image classifiers. Read more at the Oak Ridge Institute for Science and Education.