DATDroid: Dynamic Analysis Technique in Android Malware Detection

Expecting individuals’ body reaction to Covid-19 based on statistical Naïve Bayes technique

Network intrusion detection system are significant features that contribute to the enterprises and organization network success. In the past decade, Intrusion Detection system (IDS) using several methods have been proposed and implemented to safeguard the networks within an organization to be reliable, secure, and readily available. Although, some of these methods are built utilizing machine learning concepts. IDS utilizing machine learning techniques are accurate, effective and efficient in spotting attacks. However, the machine learning model performance reduces with high dimensional intrusion dataset. Therefore, it is sacrosanct to implement an efficient feature selection technique that can generate a great impact on the classification stage. Also, the feature selection phase is the most serious phase in IDS based on machine learning. This phase is expensive both in time and efforts. Furthermore, most of the proposed machine learning intrusion detection system suffered from low detection accuracy and high false positive rate when the models are experimented on high dimensional dataset. The aim of this paper is to propose a binary firefly algorithm (BFFA) based feature selection for IDS. We first performed normalization in the first stage of the model. Subsequently, the BFFA algorithm was used for feature selection stage. We adopted random forest algorithm for the classification phase. The experiment was performed on high dimensional University of New South Wales-NB 2015 (UNSW-NB15) dataset with seventy five percent of the data used for training the model and twenty percent for testing. The findings showed an accuracy of 99.72%, detection rate of 99.84%, precision of 99.27%, recall of 99.84% and F-score of 99.56%. The results were gauge with the state-of-the-art results and our results were found outstanding.

In software testing process, test data generation represents an important step for high quality software, even for mobile devices. As proposed in previous works, a potential source for random data generation is represented by the UI layout files that are used for almost all mobile platforms (Android, iOS, Windows Phone/Mobile). This paper continues the previous work and presents a test data generation system based on Android layout files. The test data generator uses DSL files as input and generates test data that conform to several testing principles. The generated test data could be stored in XML files or any format required by the testing frameworks.

Introduction Large language models (LLMs) have the potential to realize accurate risk stratification and disease prediction by integrating multimodal data, such as electronic health records, medical images, and genomic profiles. However, in complex tasks like atherosclerosis risk estimation, the design of the prompt is critical to bring out the performance of LLMs. Several researches have demonstrated that in-context learning, where the prompt contains some cases, improves the performance of LLMs when the contained cases are carefully selected. Because manual selection usually requires enormous costs, automatic case selection has been desired. Methods This study aims to improve the effectiveness of in-context learning in LLM for atherosclerosis risk prediction by introducing a strategy for case selection. Our method involves two key components: feature selection and case selection. In the feature selection phase, we compute the mutual information between the clinical features and atherosclerosis risk using the database to extract the essential clinical features. This feature selection removes the unimportant features that disturb the performance of the case selection mechanism. Then, in the case selection phase, we select several cases from the database that are the most similar to the patient being diagnosed. This study compares three metrics to compute the similarity score: - Mahalanobis distance (trained via large margin nearest neighbor classification; LMNN [1]) - Cosine similarity (between the vector representations in KNN-augmented in-context example selection; KATE [2]) - Euclidean distance (between the prompt features) This combined strategy supplies the LLM with informative cases and thereby enhances the diagnostic performance. Results We used a fine-tuned Llama3-8B model for our target language and analyzed a dataset of 117,709 cases. Each case contained 96 features that were collected from annual health check-up data. From this dataset, 1,000 cases each were randomly selected for validation and test datasets. The remaining data were used as the database in our system. We considered a binary classification task and assigned the positive label when the Cardio-Ankle Vascular Index (CAVI) was greater than 8.0. The proportion of selected features was adjusted in 10% increments to maximize the F1 score on the validation dataset. The result shows that our proposed method, the strategic feature and case selections, significantly improved the F1 score for the test dataset by around 2% compared with zero-shot prompt and random selection (see the attached table). Among three similarity metrics, Euclidean distance yielded the highest F1 scores. We also observed that the feature selection phase with the adjusted number of selected features improved the F1 score in almost all settings. Conclusion Our strategy for feature and case selections improved the performance of in-context learning for LLM-based atherosclerosis risk prediction.

Mobile devices have become widespread computing technology, people prefer to use than desktop devices. These connected devices and their features like an exchange of data, video calling etc. have made our lives simple but, this has also increased data security concerns. At present, Google's Android is dominating the market share of mobile devices; as a result, it has become a big target for malware writers. Android users can download applications from official or third-party stores. Google implements various security policies to ensure secure distribution of applications but third-party application stores have less efficient or no such policies. This makes such markets more attractive for malware writers. This paper investigates Android application security by analysing 1,946 free most downloaded Android applications in the year 2016: 1,300 from Google Play Store and 646 from third-party Android applications. 100 samples from 33 different malware families (with variants) prominent in the Android market during January 2016 to April 2016 were also collected that acted as a template for malware detection. Further, based on detected malware samples, an evaluation-based study on ten anti-malware applications is performed to identify how well they protect users from malware.

By quick computer and communication technology improvement, Distributed Denial of Service (DDoS) attack harm is getting more important. DDoS attacks research is the important study domain; a number of methods exist which have been presented like the algorithm of evolutionary as well as artificial intelligence in literature to diagnose attacks of DDoS. Unfortunately, new popular models of DDoS diagnosis are deteriorating for validating DDoS attacks objective and prior identification. Because of DDoS attack modes diversity as well as various attack traffic amount, still there is not the technique of diagnosis with promising accuracy of diagnosis currently. By choosing the best subset of features, a feature selection (FS) approach helps to shorten computing times and increase computational complexity. For mitigating attacks of denial of service, this paper applies honey badger algorithm (HBA) with algorithm of machine learning known as HBIDS. Present strategy is given the making intrusion detection system (IDS) for meeting controlled area needs and could recognize between attack and normal traffics. Moreover, HBIDS chooses the most related from basic dataset of IDS which could aid recognizing normal low-speed DDoS attacks, then chosen features are conveyed to classifiers like decision tree, multilayer perceptron, na\"ive Bayes, and support vector machine for identifying attack kind. Generally accessible dataset as CIC-IDS 2017 and KDD Cup 99 are applied for our experimental research. From simulation outcomes, this is obvious that HBIDS with decision tree needs high diagnosis with the low false–positive rate (0.001) and accuracy (99.9).

Android applications often include third-party libraries written in native code. However, current native components are not well managed by Android's security architecture. We present NativeGuard, a security framework that isolates native libraries from other components in Android applications. Leveraging the process-based protection in Android, NativeGuard isolates native libraries of an Android application into a second application where unnecessary privileges are eliminated. NativeGuard requires neither modifications to Android nor access to the source code of an application. It addresses multiple technical issues to support various interfaces that Android provides to the native world. Experimental results demonstrate that our framework works well with a set of real-world applications, and incurs only modest overhead on benchmark programs.

Congestive heart failure detection using random forest classifier

Liver disease in patients is on the rise due to environmental factors like toxic gas exposure, contaminated food, drug interactions, and excessive alcohol use. Therefore, diagnosing liver disease is crucial for saving lives and managing the condition effectively. In this paper, a new method called Liver Patients Detection Strategy (LPDS) is proposed for diagnosing liver disease in patients from laboratory data alone. The three main parts of LPDS are data preprocessing, feature selection, and detection. The data from the patient is processed, and any anomalies are removed during this stage. Then, during feature selection phase, the most helpful features are chosen. A novel method is proposed to choose the most relevant features during the feature selection stage. The formal name for this method is IB2OA, which stands for Improved Binary Butterfly Optimization Algorithm. There are two steps to IB2OA, which are; Primary Selection (PS) step and Final Selection (FS) step. This paper presents two enhancements. The first is Information Gain (IG) approach, which is used for initial feature reduction. The second is implementing BOA's initialization with Optimization Based on Opposition (OBO). Finally, five different classifiers, which are Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB), Decision Tree (DT), and Random Forest (RF) are used to identify patients with liver disease during the detection phase. Results from a battery of experiments show that the proposed IB2OA outperforms the state-of-the-art methods in terms of precision, accuracy, recall, and F-score. In addition, when compared to the state-of-the-art, the proposed model's average selected features score is 4.425. In addition, among all classifiers considered, KNN classifier achieved the highest classification accuracy on the test dataset.

This paper presents a process for extracting knowledge for physical activity recognition, from accelerometer data provided by mobile devices. Starting from a dataset collected by three different users, knowledge discovery is performed through a phase of feature extraction from raw data, minimizing the number of statistical features and optimizing the classification process. The development and comparison of classifying models over this new dataset, using both offline and online algorithms, is also described. Phases of data acquisition, pre-processing and classification are detailed, and experimental results for different machine learning algorithms are provided. For these results, different evaluation criteria are used, and the best algorithm is selected according to these criteria. Final results show success rates around 98%, while other similar works offer rates around 87%.

BackgroundExtended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E) infections are associated with high morbidity and mortality, often due to delayed initiation of carbapenem therapy. Carbapenems must be used judiciously to prevent emergence of resistant organisms. We developed a machine learning algorithm (MLA) to identify patients at increased risk for ESBL-E infections in the emergency department (ED).Figure 1:Receiver Operating Characteristic (ROC) curve for predicting Extended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E)Receiver Operating Characteristic (ROC) curve for predicting Extended-Spectrum β-Lactamase-producing Enterobacterales (ESBL-E) infections in Emergency Department Patients using a gradient boosting machine learning model. The area under the curve (AUC) is 0.8, indicating good discrimination between patients with and without ESBL-E. Higher True Positive Rate (TPR) at a low False Positive Rate (FPR) signifies better model performance.MethodsAdults (≥18) who visited an ED in the Johns Hopkins Health System between 1/2019 and 4/2024 and received Gram-negative therapies appropriate for sepsis or had documented ESBL-E infections were included. Timestamped ED vital signs, healthcare utilization, healthcare worker (HCW)-mediated patient connections, medication history, comorbidities and laboratory results populated prior to first antibiotic order were used as predictors; our primary outcome was ESBL-E infection defined by positive culture. The probability of ESBL-E infection was estimated using a gradient boosting machine learning algorithm (MLA). Because of the time-dependent nature of increasing ESBL-E infections, the MLA was derived using data from encounters prior to 7/1/2023 and evaluated in the remaining encounters using area under the operating characteristics curve (AUC) analysis.Table 1:Patient Cohort DemographicsResultsIn total there were 129,773 patient encounters included, of which 4289 (3.3%) had a positive ESBL-E sample collected during their ED encounter. Out-of-sample predictive accuracy was high (AUC 0.80; Figure). Prior HCW-mediated connections to ESBL-positive patients and prior exposure (≤6 months) to carbapenems, cephalosporins and proton pump inhibitors were the strongest predictors of ESBL-E infection. Abnormal vital signs, increased age, and prior exposure to any antibiotic (prior 6 months) were also important factors in prediction accuracy.ConclusionAn MLA using data readily available from the EHR at the time of antibiotic ordering provided good discrimination between ED patients with and without ESBL-E infection. Further refinement and implementation of MLA-driven decision-support in the EDs could drive more targeted use of broad-spectrum antibiotics and improved patient outcomes.DisclosuresJeremiah S. Hinson, MD, PhD, Beckman Coulter: Advisor/Consultant|Beckman Coulter: Grant/Research Support|Beckman Coulter: Stocks/Bonds (Private Company)

Android security implements a permission model to protect a user’s most sensitive data. These permissions regulate an app’s access to different aspects of the device, however, a fatal flaw of Android’s permission model is that it relies on the discretion of the user to determine which apps are granted permissions and which are not with limited assistance in their choice from the device. As a result, a specialized type of malware known as a logic bomb has affected Android devices. These logic bombs are designed to execute malicious code when activated by triggers, and can be designed to take advantage of users who poorly vet their applications or even hide themselves inside applications that appear to be benign. On Android, logic bombs usually carry out malicious intent by violating permissions, using a permission for some activity the user never intended. We have found 18 different permissions that applications can violate to carry out some form of malicious intent, and have developed an app, called HyenaDroid, to violate each of these permissions and create logic bombs. This provides evidence that the current Android security revolving around permissions is in need of either an update to the permissions model, or an additional system to assist the user with navigating the Android permissions model. Our research also proposes such a system, PRAST. PRAST is designed as a modular system, combining a level of efficiency that can be run during the download on an Android device, along with the effectiveness and accuracy of external analysis systems.

This paper presents an automatic fruit recognition system for classifying and identifying fruit types. The work exploits the fruit shape and color, to identify each image feature. The proposed system includes three phases namely: pre-processing, feature extraction, and classification phases. In the pre-processing phase, fruit images are resized to 90 x 90 pixels in order to reduce their color index. In feature extraction phase, the proposed system uses scale invariant feature transform (SIFT) and shape and color features to generate a feature vector for each image in the dataset. For classification phase, the proposed model applies K-Nearest Neighborhood (K-NN) algorithm classification, and support vector machine (SVM) algorithm of different kinds of fruits. A series of experiments were carried out using the proposed model on a dataset of 178 fruit images. The results of carrying out these experiments demonstrate that the proposed approach is capable of automatically recognize the fruit name with a high degree of accuracy.

BackgroundDiffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifying the distribution patterns of each feature and applying Machine Learning (ML) techniques to differentiate malignant from benign brain tumors.MethodsThis prospective study was carried out using 1599 labeled MRI brain ADC image slices, 995 malignant, 604 benign from 195 patients who were radiologically diagnosed and histopathologically confirmed as brain tumor patients. The demographics, mean pixel values, skewness, kurtosis, features of Grey Level Co-occurrence Matrix (GLCM), mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence and shade, were extracted from MRI ADC images of each patient. At the feature selection phase, the validity of the extracted features were measured using ANOVA f-test. Then, these features were used as input to several Machine Learning classification algorithms and the respective models were assessed.ResultsAccording to the results of ANOVA f-test feature selection process, two attributes: skewness (3.34) and GLCM homogeneity (3.45) scored the lowest ANOVA f-test scores. Therefore, both features were excluded in continuation of the experiment. From the different tested ML algorithms, the Random Forest classifier was chosen to build the final ML model, since it presented the highest accuracy. The final model was able to predict malignant and benign neoplasms with an 90.41% accuracy after the hyper parameter tuning process.ConclusionsThis study concludes that the above mentioned features (except skewness and GLCM homogeneity) are informative to identify and differentiate malignant from benign brain tumors. Moreover, they enable the development of a high-performance ML model that has the ability to assist in the decision-making steps of brain tumor diagnosis process, prior to attempting invasive diagnostic procedures, such as brain biopsies.

The accurate estimation of aboveground biomass (AGB) in rubber plantations is essential for predicting rubber production and assessing carbon storage. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) can obtain high spatiotemporal resolution imagery of rubber plantations, offering significant advantages in capturing fine structural details and heterogeneity. However, most previous studies primarily focused on developing biomass estimation models for rubber using machine learning (ML) algorithms in conjunction with feature selection methods based on UAV-acquired multispectral imagery. The reliance on feature selection methods limits the model’s generalizability, robustness, and predictive accuracy. In contrast, deep learning (DL) exhibits considerable promise in extracting features from high-resolution UAV-based multispectral imagery without the need for manual selection. Nonetheless, it remains unclear whether DL can surpass traditional ML methods in improving the AGB estimation accuracy in rubber plantations. To address this, our study evaluated the performance of three ML algorithms (random forest regression, RFR; XGBoost regression, XGBR; categorical boosting regression, CatBoost) combined with feature selection techniques and a deep convolutional neural network (DCNN) using multispectral imagery obtained from UAV for the AGB estimation of rubber plantations. The results indicate that the RFR combined with a principal component analysis (PCA) for feature selection yielded the best performance (R2 = 0.81, RMSE = 11.63 t/ha, MAE = 9.27 t/ha) between the three ML algorithms. Meanwhile, the DCNN model derived from the G, R, and NIR spectral bands achieved the highest estimation accuracy (R2 = 0.89, RMSE = 6.44 t/ha, MAE = 5.72 t/ha), where it outperformed the other ML methods. Our study highlights the great potential of combining UAV-based multispectral imagery with DL techniques to improve AGB estimation in rubber plantations, offering a new perspective for estimating the physiological and biochemical growth parameters of forests.