No abstract

No abstract

Abstract-The degree of imperceptibility of hidden image in the 'Digital Image Steganography' is mostly defined in relation to the limitation of Human Visual System (HVS), its chances of detection using statistical methods and its capacity to hide maximum information inside its body. Whereas, a tradeoff does exist between data hiding capacity of the cover image and robustness of underlying information hiding scheme. This paper is an exertion to underline the technique to embed information inside the cover at Stego key dependent locations, which are hard to detect, to achieve optimal security. Hence, it is secure under worst case scenario where Wendy is in possession of the original image (cover) agreed upon by Alice and Bob for their secret communication. Reliability of our proposed solution can be appreciated by observing the differences between cover, preprocessed cover and Stego object. Proposed scheme is equally good for color as well as gray scaled images. Another interesting aspect of this research is that it implicitly presents fusion of cover and information to be hidden in it while taking care of passive attacks on it.

No abstract

<abstract><p>Spam is any form of annoying and unsought digital communication sent in bulk and may contain offensive content feasting viruses and cyber-attacks. The voluminous increase in spam has necessitated developing more reliable and vigorous artificial intelligence-based anti-spam filters. Besides text, an email sometimes contains multimedia content such as audio, video, and images. However, text-centric email spam filtering employing text classification techniques remains today's preferred choice. In this paper, we show that text pre-processing techniques nullify the detection of malicious contents in an obscure communication framework. We use <italic>Spamassassin</italic> corpus with and without text pre-processing and examined it using machine learning (ML) and deep learning (DL) algorithms to classify these as ham or spam emails. The proposed DL-based approach consistently outperforms ML models. In the first stage, using pre-processing techniques, the long-short-term memory (LSTM) model achieves the highest results of 93.46% precision, 96.81% recall, and 95% F1-score. In the second stage, without using pre-processing techniques, LSTM achieves the best results of 95.26% precision, 97.18% recall, and 96% F1-score. Results show the supremacy of DL algorithms over the standard ones in filtering spam. However, the effects are unsatisfactory for detecting encrypted communication for both forms of ML algorithms.</p></abstract>