Web: http://arxiv.org/abs/2206.07953

June 17, 2022, 1:13 a.m. | Kaleab A. Kinfu, René Vidal

cs.CV updates on arXiv.org arxiv.org

Adversarial training (AT) is a simple yet effective defense against
adversarial attacks to image classification systems, which is based on
augmenting the training set with attacks that maximize the loss. However, the
effectiveness of AT as a defense for video classification has not been
thoroughly studied. Our first contribution is to show that generating optimal
attacks for video requires carefully tuning the attack parameters, especially
the step size. Notably, we show that the optimal step size varies linearly with
the …

analysis arxiv classification cv training video

More from arxiv.org / cs.CV updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY