A phishing attack is one of the most significant problems faced by online users because of its enormous effect on the online activities performed. In recent years, phishing attacks continue to escalate in frequency, severity and impact. Several solutions, using various methodologies, have been proposed in the literature to counter the web-phishing threats. Notwithstanding, the existing technology cannot detect the new phishing attacks accurately due to the insufficient integration of features of the text, image and frame in the evaluation process. The use of related features of images, frames and text of legitimate and non-legitimate websites and associated artificial intelligence algorithms to develop an integrated method to address these together. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based robust scheme using the integrated features of the text, images and frames for web-phishing detection and protection. The proposed solution achieves 98.3% accuracies. To our best knowledge, this is the first work that considers the best-integrated text, image and frame feature based solution for phishing detection scheme.
In this work, a novel lightweight and low energy encryption algorithm for voice over wireless networks is being developed and tested. The new encryption algorithm has to meet the QoS requirements of voice traffic and to be suitable for wireless devices. The goal of the research was to reduce the execution time and power consumption of the encryption process compared with the standard algorithm and at the same time at least to maintain or to increase its security level. The proposed algorithm employs similar methods with those used in the Advanced Encryption Standard algorithm (AES), with some changes and enhancements considering the limitations of wireless devices. The test results show significant improvements in new design metrics. A range of simulation scenarios are setup; testing data is analyzed to test delay, energy and security. Also, the comparison between the new algorithm and the standard one shows a significant amount of time and energy consumption reduction being achieved (approximately 35%), with good-level of complexity, making it more suitable for the wireless environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.