No abstract

ABSTRACT

ABSTRACT

Security issues are taken into consideration for many applications, where transfering sensitive data over network must be protected from any man-in-the-middle attackers. proivacy of data can be granted using encryption, by changing transmitted data into cipher form. Apart from encryption, hiding of data represents another technique to transfer data without being noticble by an attacker which is called Steganography. In this paper, we will discuss the main concepts of Steganography and a carrier media that is used for this goal.

Abstract-The need for secure communications has significantly increased with the explosive growth of the internet and mobile communications. The usage of text documents has doubled several times over the past years especially with mobile devices. In this paper, we propose a new steganography algorithm for Unicode language (Arabic). The algorithm employs some Arabic language characteristics which represent extension letters. Kashida letter is an optional property for any Arabic text and usually is not popularly used. Many algorithms tried to employ this property to hide data in Arabic text. In our method, we use this property to hide data and reduce the probability of suspicions. The proposed algorithm first introduces four scenarios to add Kashida letters. Then, random concepts are employed for selecting one of the four scenarios for each round. Message segmentation principles are also applied, enabling the sender to select more than one strategy for each block of message. At the other end, the recipient can recognize which algorithm was applied and can then decrypt then message content and aggregate it. Kashida variation algorithm can be extended to other similar Unicode languages to improve robustness and capacity.

No abstract

No abstract

Weather detection systems (WDS) have an indispensable role in supporting the decisions of autonomous vehicles, especially in severe and adverse circumstances. With deep learning techniques, autonomous vehicles can effectively identify outdoor weather conditions and thus make appropriate decisions to easily adapt to new conditions and environments. This paper proposes a deep learning (DL)-based detection framework to categorize weather conditions for autonomous vehicles in adverse or normal situations. The proposed framework leverages the power of transfer learning techniques along with the powerful Nvidia GPU to characterize the performance of three deep convolutional neural networks (CNNs): SqueezeNet, ResNet-50, and EfficientNet. The developed models have been evaluated on two up-to-date weather imaging datasets, namely, DAWN2020 and MCWRD2018. The combined dataset has been used to provide six weather classes: cloudy, rainy, snowy, sandy, shine, and sunrise. Experimentally, all models demonstrated superior classification capacity, with the best experimental performance metrics recorded for the weather-detection-based ResNet-50 CNN model scoring 98.48%, 98.51%, and 98.41% for detection accuracy, precision, and sensitivity. In addition to this, a short detection time has been noted for the weather-detection-based ResNet-50 CNN model, involving an average of 5 (ms) for the time-per-inference step using the GPU component. Finally, comparison with other related state-of-art models showed the superiority of our model which improved the classification accuracy for the six weather conditions classifiers by a factor of 0.5–21%. Consequently, the proposed framework can be effectively implemented in real-time environments to provide decisions on demand for autonomous vehicles with quick, precise detection capacity.