Our scheme constructs a composite deep learning model from the target GAN and a classifier.
In this paper, we investigate the effectiveness of data augmentation techniques in mitigating backdoor attacks and enhancing DL models' robustness.
With more and more advanced adversarial attack methods have been developed, a quantity of corresponding defense solutions were designed to enhance the robustness of DNN models.
Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
In this paper, we propose a novel watermark removal attack from a different perspective.
Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results.
In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature.
Extensive evaluations indicate that our solutions can effectively mitigate all existing standard and advanced attack techniques, and beat 11 state-of-the-art defense solutions published in top-tier conferences over the past 2 years.
This report is about applications based on spatial-frequency transform and deep learning techniques.
Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we further evaluate several tasks of few-shot expression learning by virtue of our F2ED, which are to recognize the facial expressions given only few training instances.
With more encrypted network traffic gets involved in the Internet, how to effectively identify network traffic has become a top priority in the field.
First, we create a new facial expression dataset of more than 200k images with 119 persons, 4 poses and 54 expressions.