4 papers
Adversarial Attack on Deep Learning-Based Splice Localization
Andras Rozsa, Zheng Zhong, Terrance E. Boult
Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices. Recent best performing image-forensics algorithms…
Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations
Andras Rozsa, Terrance E. Boult
Adversarial examples contain small perturbations that can remain imperceptible to human observers but alter the behavior of even the best performing deep learning models and yield…
Adversarial Robustness: Softmax versus Openmax
Andras Rozsa, Manuel Günther, Terrance E. Boult
Deep neural networks (DNNs) provide state-of-the-art results on various tasks and are widely used in real world applications. However, it was discovered that machine learning model…
Adversarial Diversity and Hard Positive Generation
Andras Rozsa, Ethan M. Rudd, Terrance E. Boult
State-of-the-art deep neural networks suffer from a fundamental problem - they misclassify adversarial examples formed by applying small perturbations to inputs. In this paper, we…