IEEE

Benchmarking Image Classifiers for Physical Out-of-Distribution Examples Detection

Abstract: The rising popularity of deep neural networks (DNNs) in computer vision has raised concerns about their robustness in the real world. Recent works in this field have well-demonstrated the ...
IEEE

Minimizing Adversarial Training Samples for Robust Image Classifiers: Analysis and Adversarial Example Generator Design

Abstract: Training deep neural networks (DNNs) with altered data, known as adversarial training, is essential for improving their robustness. A significant challenge emerges as the robustness ...
The Guardian

White House doctoring Minnesota woman’s photo unlikely to derail case, say experts

Altered image shows Nekima Levy Armstrong sobbing after arrest during protest outside a Minneapolis church The White House’s decision to post a doctored photo of a woman arrested in Minneapolis on ...
The Guardian

White House posts digitally altered image of woman arrested after ICE protest

Guardian analysis shows images are the same, with Nekima Levy Armstrong looking composed in original but sobbing after alteration The White House posted a digitally altered image of a woman who was ...