Web: http://arxiv.org/abs/2206.10858

June 23, 2022, 1:10 a.m. | Changming Xu, Gagandeep Singh

cs.LG updates on arXiv.org arxiv.org

Universal Adversarial Perturbations (UAPs) are imperceptible, image-agnostic
vectors that cause deep neural networks (DNNs) to misclassify inputs from a
data distribution with high probability. Existing methods do not create UAPs
robust to transformations, thereby limiting their applicability as a real-world
attacks. In this work, we introduce a new concept and formulation of robust
universal adversarial perturbations. Based on our formulation, we build a
novel, iterative algorithm that leverages probabilistic robustness bounds for
generating UAPs robust against transformations generated by composing …

arxiv lg

More from arxiv.org / cs.LG 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