RepackDroid: An Efficient Detection Model for Repackaged Android Applications

Image classification is a very popular machine learning domain in which deep convolutional neural networks have mainly emerged on such applications. These networks manage to achieve remarkable performance in terms of prediction accuracy but they are considered as black box models since they lack the ability to interpret their inner working mechanism and explain the main reasoning of their predictions. There is a variety of real world tasks, such as medical applications, in which interpretability and explainability play a significant role. Making decisions on critical issues such as cancer prediction utilizing black box models in order to achieve high prediction accuracy but without provision for any sort of explanation for its prediction, accuracy cannot be considered as sufficient and ethnically acceptable. Reasoning and explanation is essential in order to trust these models and support such critical predictions. Nevertheless, the definition and the validation of the quality of a prediction model’s explanation can be considered in general extremely subjective and unclear. In this work, an accurate and interpretable machine learning framework is proposed, for image classification problems able to make high quality explanations. For this task, it is developed a feature extraction and explanation extraction framework, proposing also three basic general conditions which validate the quality of any model’s prediction explanation for any application domain. The feature extraction framework will extract and create transparent and meaningful high level features for images, while the explanation extraction framework will be responsible for creating good explanations relying on these extracted features and the prediction model’s inner function with respect to the proposed conditions. As a case study application, brain tumor magnetic resonance images were utilized for predicting glioma cancer. Our results demonstrate the efficiency of the proposed model since it managed to achieve sufficient prediction accuracy being also interpretable and explainable in simple human terms.

As there has been a paradigm shift in the learning load from a human subject to a computer, machine learning has been considered as a useful tool for Brain-Computer Interfaces (BCIs). In this paper, we propose a novel Bayesian framework for discriminative feature extraction for motor imagery classification in an EEG-based BCI in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches. In our framework, the problem of simultaneous spatiospectral filter optimization is formulated as the estimation of an unknown posterior probability density function (pdf) that represents the probability that a single-trial EEG of predefined mental tasks can be discriminated in a state. In order to estimate the posterior pdf, we propose a particle-based approximation method by extending a factored-sampling technique with a diffusion process. An information-theoretic observation model is also devised to measure discriminative power of features between classes. From the viewpoint of classifier design, the proposed method naturally allows us to construct a spectrally weighted label decision rule by linearly combining the outputs from multiple classifiers. We demonstrate the feasibility and effectiveness of the proposed method by analyzing the results and its success on three public databases.

While Android has become most popular OS in mobile phone market, more and more Android app developers are suffering from intellectual property infringement because it’s easy to extract the assets stored in the Android apps and to decompile Android apps to Java source code. This issue also poses threats to users’ privacy. In this article we reviewed the existing protection approaches for the protection of the source code and assets in Android apps, demonstrated the reason why Java Native Interface (JNI) approach can help improve the protection provided by existing approaches, developed 4 Android demo apps with 2 experiments conducted to evaluate the effectiveness of protection provided by the combination of Encryption and JNI approaches.

A novel multi-feature extraction based automatic modulation classification

Managing privacy leakage is of great importance in the Android platform. The variety of new user-privacy fraud reveals a new challenge in predicting potential privacy disclosure threats and protecting the privacy inside our pocket. In this paper, we present an analysis framework, called AppLeak, for information loss evaluation, privacy leakage detection, and privacy risk assessment on Android applications. With newly formalized privacy measures, AppLeak can effectively and efficiently support mobile user in identifying privacy risks of specific mobile applications.

The most popular approach for document representation is the bag-of-words where terms are considered as features. In order to compute the values of these features, the term frequencies are generally scaled by a collection frequency factor to take into account the relative importance of different terms. The term frequencies can be considered as raw data about the input document. In this study, a novel framework for feature extraction is proposed for binary text classification where feature extraction is defined as a single variable classification problem. The term frequencies are the inputs and the output of each classifier is used to define a triple of features for the corresponding term. The magnitude of the classifier output that is in the interval [0.5,1] is an indicator for the confidence of the classifier and it is also employed in document representation together with the term frequency and the collection frequency factor.

Tensor-Cuts: A simultaneous multi-type feature extractor and classifier and its application to road extraction from satellite images

In this paper, we have done detection of android malware using static and dynamic analysis. This approach also knows as hybrid approach. Our goal is to find recent vulnerabilities in social engineering applications which cannot be detected by modern antivirus or online scanners. The hackers inject malicious code into benign application modify the nature of code and hence forth strength attack can be polymorphic or stealth techniques. We are building model using supervised learning applying SVM (Supervised Learning Machine) taking features as input and label for decision whether malicious or benign application also added hyper parameter tuned for obtaining better accuracy rate. By using this classifier, we can make binary classification and henceforth suggest a decision support system for end user to protect themselves from recent threats that can come to their android application.

Aim: The present study was conducted with the aim of formulating a model of marital distress based on communication patterns and attachment styles with the mediating role of resilience in homemaker women. Methods: The present research had an applied objective and utilized a descriptive correlational method with a path analysis design for data collection. The statistical population of this study consisted of all homemaker women in the Narges Akbatan Community Group in Tehran during the first three months of the year 1401 (Solar Hijri calendar), from which 384 individuals were selected as the sample group, using convenience sampling. The research instruments included the Marital Distress Questionnaire, Communication Patterns Questionnaire, Attachment Styles Questionnaire, and Resilience Scale. Finally, the data were analyzed using the linear regression method within the path analysis framework, utilizing SPSS24 and AMOS23 software for statistical analysis. Findings: The results showed that communication patterns, secure and anxious attachment styles have a direct relationship with marital distress in homemaker women (p < 0.01). Moreover, resilience was able to mediate the relationship between communication patterns and marital distress, as well as the relationship between secure and avoidant attachment styles and marital distress in homemaker women (p < 0.01). Conclusion: The findings of this research indicate that in order to reduce marital distress in homemaker women, identifying couples' communication styles and attempting to change unhealthy communication patterns, through resilience-based training, counseling, and other interventions, can be effective.

In the context of intelligent power system construction, power grid operational data exhibits highdimensional, non-linear, and strong stochastic fluctuation characteristics. To address the urgent demand for high-precision signal feature extraction, data privacy, and cross-domain collaborative analysis in complex environments, Federated MetaReinforcement Learning (FMRL) has emerged as an advanced paradigm for solving heterogeneous data analysis challenges. This paper constructs a signal feature extraction and fluctuation analysis framework based on FMRL for scenarios involving multiple grid operators. Distinct from traditional methods that rely on fixed optimization strategies, we formulate the crossdomain training process as a bilevel optimization problem. We define the optimization objective (i.e., the reward function) as maximizing the validation accuracy improvement of the signal reconstruction task. Accordingly, a Meta-RL Agent is designed to act as a hyper-parameter controller, which dynamically adjusts the local learning rate by perceiving the training status (State), thereby enabling rapid adaptation to Non-IID (Non-Identically and Independently Distributed) data distributions. The framework utilizes a hybrid ResNet-BiLSTM neural network as the base feature extractor, where ResNet captures spatial structural features and BiLSTM extracts long-term temporal dependencies. Targeting communication security, we propose a privacy-preserving algorithm based on meta-policy aggregation and Homomorphic Encryption (HE). Through a secure metapolicy update mechanism on the central server, efficient convergence and knowledge fusion are achieved without local raw signals leaving their respective domains. Simulation results demonstrate that, compared to state-of-the-art federated metalearning benchmarks, the proposed FMRL algorithm significantly improves signal fluctuation fitting ability and cross-domain adaptability, while effectively guaranteeing data privacy and model security.

Attention mechanism is useful in spatio-temporal wind speed prediction: Evidence from China

The polynomial neural network, or called polynomial network classifier (PNC), is a powerful nonlinear classifier that can separate classes of complicated distributions. A method that expands polynomial terms on principal subspace has yielded superior performance. In this paper, we aim to further improve the performance of the subspace-feature-based PNC. In the framework of discriminative feature extraction (DFE), we adjust the subspace parameters together with the network weights in supervised learning. Under the objective of minimum squared error, the parameters can be efficiently updated by stochastic gradient descent. In experiments on 13 datasets from the UCI Machine Learning Repository, we show that DFE can either improve the classification accuracy or reduce the network complexity. On seven datasets, the accuracy of PNC is competitive with support vector classifiers.KeywordsLinear Discriminant AnalysisNetwork WeightStochastic Gradient DescentPolynomial TermFisher Linear Discriminant AnalysisThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A cutting-edge framework for damage-sensitive feature extraction leveraging modal dynamic flexibility in signal processing-driven structural health monitoring

Retinopathy of prematurity (ROP) is a retinal vascular disease that primarily affects premature infants with low birth weight. It is a leading cause of childhood blindness worldwide, but it can often be effectively managed with appropriate and timely diagnosis and treatment. To address the impact of image style on model classification performance, this paper proposes a dual-scale Swin Transformer (DS-Swin-T) network for ROP. The network comprises three components: image synthesis (IS), feature alignment, and advanced adversarial learning. The IS module generates synthesis style images as an intermediate latent space between source and target styles, reducing style difference. The DS-Swin-T serves as the primary framework for image feature extraction. Detail and style encoders extract features in the shallow feature space, with detail and style losses aligning these features to ensure consistency across styles. To extract rich style-invariant features and ensure consistent classification within the same category, adversarial learning is applied in the advanced feature space. Finally, feature fusion units process dual-scale classification representations. Our method achieves an average accuracy of 97.91% on the source style dataset. When transferred to other target style datasets, our method effectively mitigates the performance degradation caused by style difference, reaching a maximum average accuracy of 93.66%. Extensive experiments demonstrate the effectiveness of our method.

Based on the powerful feature extraction capability of deep convolutional neural networks, image-level retrieval methods have achieved superior performance compared to the hand-crafted features and indexing algorithms. However, people tend to focus on foreground objects of interest in images. Locating objects accurately and using object-level features for retrieval become the essential tasks of instance search. In this work, we propose a novel instance retrieval method FRWACE, which combines the Faster R-CNN framework for object-level feature extraction with a brand-new Wasserstein Convolutional Auto-encoder for dimensionality reduction. In addition, we propose a considerate category-first spatial re-rank strategy to improve instance-level retrieval accuracy. Extensive experiments on four large datasets Oxford 5K, Paris 6K, Oxford 105K and Paris 106K show that our approach has achieved significant performance compared to the state-of-the-arts.