Search

The risk of copyrighted data theft has increased with the growth of digital communication and easy access to digital data. Using watermarking methods has always been an active research subject against unauthorized users to protect copyrighted data. Deep watermarking methods were introduced in recent years to face this challenge, however, the robustness of these methods against graphic attacks and generating high-quality marked-images are still one of the important challenges in this issue. Also, exposure of these methods to the risk of intellectual property infringement is another important challenge in this subject. To address the quality degradation challenge of marked-images, we propose a blind deep image-watermarking method inspired by the Siamese network in which the watermark-codes will be embedded in the network's weights instead of cover-images. Also, a cover-atmosphere is defined for each cover-image which includes the cover-image and its various attacked versions. Favorable robustness is achieved by mapping each cover-atmosphere to its corresponding watermark-code space. Moreover, an independent subspace for non-watermark-images is considered to map into a null-code which makes the method robust against intellectual property infringement attack. The results obtained from the experiment show that the suggested approach outperforms existing methods and can withstand different types of graphical and surrogate model attacks. [ABSTRACT FROM AUTHOR]

The "curse of dimensionality" issue caused by high-dimensional datasets not only imposes high memory and computational costs but also deteriorates the capability of learning methods. The main purpose of feature selection is to reduce the dimensionality of these datasets by discarding redundant and irrelevant features, which improves the performance of the learning algorithm. In this paper, a new feature selection algorithm, referred to as FSBACOM, was presented based on the binary ant system (BAS). The proposed method sought to improve feature selection by decreasing redundancy and achieved an optimum solution by increasing search space in a short time. For this purpose, the features were organized sequentially in a circular graph, where each feature was connected to the next one with two select/deselect edges. The proposed representation of the search space reduced computational time significantly, particularly on the high-dimensional datasets. Inspired from genetic algorithm and simulated annealing, a damped mutation strategy was introduced to avoid falling into local optima. In addition, a new idea was utilized to reduce the redundancy between selected features as far as possible. The performance of the proposed algorithm was compared to that of state-of-the-art feature selection algorithms using different classifiers on real-world datasets. The experimental results confirmed that FSBACOM significantly reduces computational time and achieves better performance than other feature selection methods. [ABSTRACT FROM AUTHOR]