Image dehazing aims to recover the uncorrupted content from a hazy image. Instead of leveraging traditional lowlevel or handcrafted image priors as the restoration constraints, e.g., dark channels and increased contrast, we propose an end-to-end gated context aggregation network to directly restore the final haze-free image. In this network, we adopt the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters, and leverage a gated sub-network to fuse the features from different levels. Extensive experiments demonstrate that our method can surpass previous state-of-the-art methods by a large margin both quantitatively and qualitatively. In addition, to demonstrate the generality of the proposed method, we further apply it to the image deraining task, which also achieves the state-of-the-art performance. Code has been made available at https://github.com/cddlyf/GCANet.

Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Moreover, adversarial examples can be used to perform an attack on various kinds of DNN based systems, even if the adversary has no access to the underlying model. Many defense methods have been proposed, such as obfuscating gradients of the networks or detecting adversarial examples. However it is proved out that these defense methods are not effective or cannot resist secondary adversarial attacks. In this paper, we point out that steganalysis can be applied to adversarial examples detection, and propose a method to enhance steganalysis features by estimating the probability of modifications caused by adversarial attacks. Experimental results show that the proposed method can accurately detect adversarial examples. Moreover, secondary adversarial attacks cannot be directly performed to our method because our method is not based on a neural network but based on high-dimensional artificial features and FLD (Fisher Linear Discriminant) ensemble.

In current years data hiding has been proposed as a likely technique for the purpose of information security. RIT-based on allows the user to convert the content of original image into the content of another target image with the same size. The transformed image, which looks like the target image, is used as the "encrypted image," and is outsourced to the cloud. Therefore, the cloud server can easily embed data into the "encrypted image" If the receiver has both the data hiding key and the encryption key, can extract the additional data and recover the original content. Main objective of this paper to provide an efficient data hiding technique and image Encryption in which the data and image can be retrieving. Data concealment by Adaptive least significant bit replacement. Two RDH method including traditional use of block pairing and block transformation different needs on image quality.

No abstract

No abstract