In recent years, Android malware has continued to grow at an alarming rate. More recent malicious apps’ employing highly sophisticated detection avoidance techniques makes the traditional machine learning based malware detection methods far less effective. More specifically, they cannot cope with various types of Android malware and have limitation in detection by utilizing a single classification algorithm. To address this limitation, we propose a novel approach in this paper that leverages parallel machine learning and information fusion techniques for better Android malware detection, which is named Mlifdect. To implement this approach, we first extract eight types of features from static analysis on Android apps and build two kinds of feature sets after feature selection. Then, a parallel machine learning detection model is developed for speeding up the process of classification. Finally, we investigate the probability analysis based and Dempster-Shafer theory based information fusion approaches which can effectively obtain the detection results. To validate our method, other state-of-the-art detection works are selected for comparison with real-world Android apps. The experimental results demonstrate that Mlifdect is capable of achieving higher detection accuracy as well as a remarkable run-time efficiency compared to the existing malware detection solutions.

Personalised recommendation is a difficult problem that has received a lot of attention to academia and industry. Because of the sparse user–item interaction, cold-start recommendation has been a particularly difficult problem. Some efforts have been made to solve the cold-start problem by using model-agnostic meta-learning on the level of the model and heterogeneous information networks on the level of data. Moreover, using the memory-augmented meta-optimisation method effectively prevents the meta-learning model from entering the local optimum. As a result, this paper proposed memory-augmented meta-learning on meta-path, a new meta-learning method that addresses the cold-start recommendation on the meta-path furthered. The meta-path builds at the data level to enrich the relevant semantic information of the data. To achieve fast adaptation, semantic-specific memory is utilised to conduct the model with semantic parameter initialisation, and the method is optimised by a meta-optimisation method. We put this method to the test using two widely used recommended data set and three cold-start scenarios. The experimental results demonstrate the efficiency of our proposed method.

Recently, security incidents such as sensitive data leakage and video/audio hardware control caused by Android malware have raised severe security issues that threaten Android users, so thus behavior analysis and detection research researches of malicious Android applications have become a hot topic. However, the behavioral portrait of Android malware that can depict the behavior of Android malware is not approached in previous literature. To fill this gap, we propose DroidPortrait, an Android malware multi-dimensional behavioral portrait construction approach. We take the behavior of Android malware as an entry point and extract an informative behavior dataset that includes static and dynamic behavior from Android malware. Next, aiming at Android malware that contains different kinds of behaviors, a behavioral tag is defined then combined with a machine learning (ML) algorithm to implement the correlation of these behavioral tags. Android malware behavioral portrait architecture based on behavior analysis and its design is investigated, as also an optimized random forest algorithm is conceived then combined with Android malware behavioral portrait to detect Android malware. The evaluation findings indicate the DroidPortrait can depict behavioral characteristics of Android malware comprehensive and detect them with high performance.

Reconstructing a 3D human body mesh from a monocular image is a challenging inverse problem because of occlusion and complicated human articulations. Recent deep learning-based methods have made significant progress in single-image human reconstruction. Most of these works are either model-based methods, which estimate the sparse parameters of a statistical human body model, or model-free methods, which directly recover the vertices' coordinates of a predefined mesh. However, model-based methods always suffer detail losses due to the limited parameter space, and model-free methods are hard to directly recover satisfactory results from images due to the use of a shared global feature for all vertices and the domain gap between 2D regular images and 3D irregular meshes. To resolve these issues, we propose a hybrid model, which combines the advantages of both model-based approach and model-free approach to estimate a 3D human mesh in a coarse-to-fine manner. Initially, we utilize a convolutional neural network (CNN) to estimate the parameters of a Skinned Multi-Person Linear Model (SMPL), which allows us to generate a coarse human mesh. After that, the vertex coordinates of the coarse human mesh are further refined by a graph convolutional neural network (GCN). Unlike previous GCN-based methods, whose vertex coordinates are recovered from a shared global feature, we propose a LOcal CorRespondence-Aware (LOCRA) module to extract local special features for each vertex. To make the local features related to the human pose, we also add a keypoint-related loss to supervise the training process of the LOCRA module. Experiments demonstrate that our hybrid model with the LOCRA module outperforms existing methods on multiple public benchmarks. Our code will be publicly available.

Recently, brain-machine interfacing is very popular that link humans and artificial devices through brain signals which lead to corresponding mobile application as supplementary. The Android platform has developed rapidly because of its good user experience and openness. Meanwhile, these characteristics of this platform, which cause the amazing pace of Android malware, pose a great threat to this platform and data correction during signal transmission of brain-machine interfacing. Many previous works employ various behavioral characteristics to analyze Android application (or app) and detect Android malware to protect signal data secure. However, with the development of Android app, category of Android app tends to be diverse, and the Android malware behavior tends to be complex. This situation makes existing Android malware detections complicated and inefficient. In this paper, we propose a broad analysis, gathering as many behavior characteristics of an app as possible and compare these behavior characteristics in several metrics. First, we extract static and dynamic behavioral characteristic from Android app in an automatic manner. Second, we explain the decision we made in each kind of behavioral characteristic we choose for Android app analysis and Android malware detection. Third, we design a detailed experiment, which compare the efficiency of each kind of behavior characteristic in different aspects. The results of experiment also show Android malware detection performance of these behavior characteristics combine with well-known machine learning algorithms.

Adversarial robustness is an important consideration for the deployment of artificial intelligence-based intrusion detection systems (IDSs). Existing studies have developed various defense strategies and commonly evaluate them using individual performance measures. However, selecting an appropriate defense strategy remains challenging because different strategies may exhibit distinct advantages under different evaluation objectives and deployment requirements. This study formulates adversarial IDS defense selection as a multi-objective decision problem and proposes a backbone-conditioned preference-aware Pareto analysis framework. The proposed framework evaluates candidate defense strategies from four dimensions. Security threshold filtering is first applied to remove strategies that fail to satisfy minimum robustness requirements, followed by Pareto analysis to identify non-dominated candidates. A preference-aware selection mechanism is then employed to determine the most suitable defense strategy according to different deployment priorities. Experiments on the UNSW-NB15 dataset with multiple IDS backbones demonstrate that the proposed framework can effectively reveal the trade-offs among defense strategies. The results further show that defense selection is influenced by both deployment preferences and backbone architectures, indicating that no single defense strategy is universally optimal across different scenarios. These findings highlight the importance of multi-objective analysis and preference-aware decision-making for adversarial IDS defense strategy selection.