Many smart mobile devices, including smartphones, smart televisions, smart watches, and smart vacuums, have been powered by Android devices. Therefore, mobile devices have become the prime target for malware attacks due to their rapid development and utilization. Many security practitioners have adopted different approaches to detect malware. However, its attacks continuously evolve and spread, and the number of attacks is still increasing. Hence, it is important to detect Android malware since it could expose a great threat to the users. However, in machine learning intelligence detection, too many insignificant features will decrease the percentage of the detection’s accuracy. Therefore, there is a need to discover the significant features in a minimal amount to assist with machine learning detection. Consequently, this study proposes the Pearson correlation coefficient (PMCC), a coefficient that measures the linear relationship between all features. Afterwards, this study adopts the heatmap method to visualize the PMCC value in the color of the heat version. For machine learning classification algorithms, we used a type of fuzzy logic called lattice reasoning. This experiment used real 3799 Android samples with 217 features and achieved the best accuracy rate of detection of more than 98% by using Unordered Fuzzy Rule Induction (FURIA).
In the present, watermark plays an important part in all copyrighted content whether it is physical or digital. The importance of watermark in digital data increases as the usage of internet in transferring data increases day by day as the technologies improves. The main objective of using digital watermark is to apply the highest security as possible to the digital image and in the same time to reduce as most disturbance as possible that can be visible to the human eye. This research proposed a hybrid mapping pattern which is Hilbert-Peano Curve to try to achieve the highest security as possible from alteration. This proposed digital watermark uses the Least Significant Bit (LSB) to store the watermark data, which consist of parity bits as the authentication data and recovery data. This is to reduce the disturbance to the original image as much as possible as it might alter the colour of the original image. The results are compared with the existing watermark, Hilbert-LSB to analyse which pattern is suitable to be implemented with the watermarking scheme. The results of this research shows Hilbert-Peano pattern can contribute better performance in terms of watermark data security, time taken to embed watermark data, and the imperceptibility level if compared to the original Hilbert mapping pattern.
The 21st century might be considered the "boom" period for social networking due to the fast expansion of social media use. In terms of user privacy and security regulations, a plethora of new requirements, issues, and concerns have arisen due to the proliferation of social media. With the increase in social media use, images on social media are often modified or fabricated for certain purposes. Therefore, this work implements and evaluates the SPIRAL-LSB algorithm for common attacks for social media images. Image compression was also discussed as images published to social media platforms was often compressed. An analysis was performed to assess the algorithm's output on social media images. The experiments were carried out prior to and after uploading to the Instagram platform. The dataset was subjected to image splicing, copy-move, cut-andpaste, text insertion, and 3D-sticker insertion attacks. The outcome of SPIRAL-LSB was effective for text insertion attacks solely. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) were selected as the experiment's metrics. The average PSNR value is 63.25, and the SSIM value is 0.99964, both of which are regarded high. This indicates that the watermark has not degraded the quality of the images. This work was designed for usage on social media for intellectual property reasons and may be used to validate the validity of social media images and prevent issues with image integrity, such as image manipulation.
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.