Malware applications (Apps) targeting mobile devices are widespread, and compromise the sensitive and private information stored on the devices. This is due to the asymmetry between informative permissions and irrelevant and redundant permissions for benign Apps. It also depends on the characteristics of the Android platform, such as adopting an open-source policy, supporting unofficial App stores, and the great tolerance for App verification; therefore the Android platform is destined to face such malicious intrusions. In this paper, we propose a permissions-based malware detection system (PerDRaML) that determines the App’s maliciousness based on the usage of suspicious permissions. The system uses a multi-level based methodology; we first extract and identify the significant features such as permissions, smali sizes, and permission rates from a manually collected dataset of 10,000 applications. Further, we employ various machine learning models to categorize the Apps into their malicious or benign categories. Through extensive experimentations, the proposed method successfully identifies the 5× most significant features to predict malicious Apps. The proposed method outperformed the existing techniques by achieving high accuracies of malware detection i.e., 89.7% with Support Vector Machine, 89.96% with Random Forest, 86.25% with Rotation Forest, and 89.52% with Naïve Bayes models. Moreover, the proposed method optimized up to ~77% of the feature set as compared to the recent approaches, while improving the evaluation metrics such as precision, sensitivity, accuracy, and F-measure. The experimental results show that the proposed system provides a high level of symmetry between irrelevant permissions and malware Apps. Further, the proposed system is promising and may provide a low-cost alternative for Android malware detection for malicious or repackaged Apps.

Steganography is the art and practice of communication using hidden messages. The least significant bits (LSB) based method is the well-known type of steganography in the spatial domain. Usually, achieving the larger embedding capacity in LSB-based methods requires a large number of LSB bits modification which indirectly reduces the visual quality of stego-image and increases the risk of steganalysis detection attacks. In this study, we propose a novel steganography method with data mapping strategy which can reduce the number of bits modification per pixel. In the proposed method, four secret data bits are mapped with the four most significant bits of a cover pixel. Furthermore, the only two LSBs of a pixel are modified to indicate the mapping strategy. Experimental results show that the proposed method is able to achieve 3.48% larger embedding capacity while enhancing the visual quality (i.e., peak signal to noise ratio (PSNR) 3.73 dB) and reducing the modification of 0.76 bits per pixel. Moreover, the proposed method provides security against basic Regular and Singular groups (RS) steganalysis and histogram steganalysis detection attacks.

Human Activity Recognition is a key component of ambient assisted living and one of the most active areas of research in the Internet of Things. The use of wearable and embedded sensors in human activity recognition overcomes the limitations of conventional approaches relying on machine vision and environmental sensors. We offer a novel, lightweight Convolutional Neural Network – Bidirectional Gated Recurrent Unit (CNN-BiGRU) model that classifies human activities using the inertial sensor data collected with body-mounted smartwatches and smartphones. Unlike the traditional approaches, the presented model is trained on the magnitude of the 3D acceleration (mag _a ), which significantly minimizes the input space 1D. The deep learner has been validated using two different publicly available datasets from the Wireless Sensor Data Mining (WISDM) lab and different evaluation parameters such as Recall/Sensitivity, Precision, accuracy, and F1-scores are computed. A comparison with the existing studies reveals that our proposed learner surpasses the existing methodologies. Using magnitude of 3D acceleration (mag _a ^w , 1D input signal), we have achieved 97.29% accuracy for all 6 activities of WISDM 2011 dataset and 98.81% accuracy for 3D acceleration (a _x ^w ,a _y ^w ,a _z ^w ). The Precision, Recall and F1-score remained at 97% for the 1D case and 99% for the 3D case. When evaluated on the data of all 18 smartwatch-based activities in WISDM 2019 dataset, we have achieved 97.5% accuracy with the magnitude of 3D acceleration (mag _a ^w ) and 98.4% accuracy for 6D acceleration and angular velocities (a _x ^w ,a _y ^w ,a _z ^w ,ω _x ^w ,ω _y ^w ,ω _z ^w ). The Precision, Recall and F1-score remained at 98% in both cases.

Falling poses a significant challenge to the health and well-being of the elderly and people with various disabilities. Precise and prompt fall detection plays a crucial role in preventing falls and mitigating the impact of injuries. In this research, we propose a deep classifier for pre-impact fall detection which can detect a fall in the pre-impact phase with an inference time of 46–52 milliseconds. The proposed classifier is an ensemble of Convolutional Neural Networks (CNNs) and Bidirectional Gated Recurrent Units (BiGRU) with residual connections. We validated the performance of the proposed classifier on a comprehensive, publicly available preimpact fall dataset. The dataset covers 36 diverse activities, including 15 types of fall-related activities and 21 types of activities of daily living (ADLs). Furthermore, we evaluated the proposed model using three different inputs of varying dimensions: 6D input (comprising 3D accelerations and 3D angular velocities), 3D input (3D accelerations), and 1D input (magnitude of 3D accelerations). The reduction in the input space from 6D to 1D is aimed at minimizing the computation cost. We have attained commendable results outperforming the state-of-the-art approaches by achieving an average accuracy and F1 score of 98% for 6D input size. The potential implications of this research are particularly relevant in the realm of smart healthcare, with a focus on the elderly and differently-abled population.

Instant messaging applications (apps) have played a vital role in online interaction, especially under COVID-19 lockdown protocols. Apps with security provisions are able to provide confidentiality through end-to-end encryption. Ill-intentioned individuals and groups use these security services to their advantage by using the apps for criminal, illicit, or fraudulent activities. During an investigation, the provision of end-to-end encryption in apps increases the complexity for digital forensics investigators. This study aims to provide a network forensic strategy to identify the potential artifacts from the encrypted network traffic of the prominent social messenger app Signal (on Android version 9). The analysis of the installed app was conducted over fully encrypted network traffic. By adopting the proposed strategy, the forensic investigator can easily detect encrypted traffic activities such as chatting, media messages, audio, and video calls by looking at the payload patterns. Furthermore, a detailed analysis of the trace files can help to create a list of chat servers and IP addresses of involved parties in the events. As a result, the proposed strategy significantly facilitates extraction of the app’s behavior from encrypted network traffic which can then be used as supportive evidence for forensic investigation.