Deep learning has been widely applied in various fields such as computer vision, natural
language processing, and data mining. Although deep learning has achieved significant …

Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …

Strong theoretical guarantees of robustness can be given for ensembles of classifiers
generated by input randomization. Specifically, an $\ell_2 $ bounded adversary cannot alter …

It is a challenging task to fool an image classifier based on deep neural networks under the
black-box setting where the target model can only be queried. Among existing black-box …

In this work we revisit gradient regularization for adversarial robustness with some new
ingredients. First, we derive new per-image theoretical robustness bounds based on local …

As an effective black-box adversarial attack, decision-based methods polish adversarial
noise by querying the target model. Among them, boundary attack is widely applied due to …

Constructing adversarial perturbations for deep neural networks is an important direction of
research. Crafting image-dependent adversarial perturbations using white-box feedback …

Text-to-Image (T2I) models have raised security concerns due to their potential to generate
inappropriate or harmful images. In this paper, we propose UPAM, a novel framework that …

Neural network quantization has become increasingly popular due to efficient memory
consumption and faster computation resulting from bitwise operations on the quantized …

Deep neural networks provide good performance in the fields of image recognition, speech
recognition, and text recognition. For example, recurrent neural networks are used by image …