Intelligent Mobile Malware Detection

Despite the growing threat posed by the Android malware, the research community is still lacking a comprehensive view of common behaviors and emerging trends in malware families active on the platform. Without such view, researchers incur the risk of developing systems that only detect outdated threats, missing the most recent ones. In this article, we conduct the largest measurement of Android malware behavior to date, analyzing over 1.2 million malware samples that belong to 1.28K families over a period of eight years (from 2010 to 2017). We aim at understanding how Android malware has evolved over time, focusing on <i>repackaging</i> malware. In this type of threat different innocuous apps are piggybacked with a malicious payload (<i>rider</i>), allowing inexpensive malware manufacturing. One of the main challenges posed when studying repackaged malware is slicing the app to split benign components apart from the malicious ones. To address this problem, we use differential analysis to isolate software components that are irrelevant to the campaign and study the behavior of malicious riders alone. Our analysis framework relies on collective repositories and recent advances on the systematization of intelligence extracted from multiple anti-virus vendors. We find that since its infancy in 2010, the Android malware ecosystem has changed significantly, both in the type of malicious activity performed by malware and in the level of obfuscation used to avoid detection. Finally, we discuss what our findings mean for Android malware detection research, highlighting areas that need further attention by the research community. In particular, we show that riders of malware families evolve over time. This evidences important experimental bias in research works levering on automated systems for family identification without considering variants.

FAGnet: Family-aware-based android malware analysis using graph neural network

Mobile malware detection has attracted massive research effort in our community. A reliable and up-to-date malware dataset is critical to evaluate the effectiveness of malware detection approaches. Essentially, the malware ground truth should be manually verified by security experts, and their malicious behaviors should be carefully labelled. Although there are several widely-used malware benchmarks in our community (e.g., MalGenome, Drebin, Piggybacking and AMD, etc.), these benchmarks face several limitations including out-of-date, size, coverage, and reliability issues, etc. In this paper, we first make efforts to create MalRadar, a growing and up-to-date Android malware dataset using the most reliable way, i.e., by collecting malware based on the analysis reports of security experts. We have crawled all the mobile security related reports released by ten leading security companies, and used an automated approach to extract and label the useful ones describing new Android malware and containing Indicators of Compromise (IoC) information. We have successfully compiled MalRadar, a dataset that contains 4,534 unique Android malware samples (including both apks and metadata) released from 2014 to April 2021 by the time of this paper, all of which were manually verified by security experts with detailed behavior analysis. Then we characterize the MalRadar dataset from malware distribution channels, app installation methods, malware activation, malicious behaviors and anti-analysis techniques. We further investigate the malware evolution over the last decade. At last, we measure the effectiveness of commercial anti-virus engines and malware detection techniques on detecting malware in MalRadar. Our dataset can be served as the representative Android malware benchmark in the new era, and our observations can positively contribute to the community and boost a series of research studies on mobile security.

Currently the android platform is that the quickest growing hand-held OS package. And it’s become the foremost desirable and viable objective of malevolent applications. Android malware growth has been increasing dramatically in conjunction with increasing the variety and guiltiness of their developing techniques. Mobile malware is therefore pernicious and, on the increase, consequently having a quick and reliable detection system is important for the users. Subtle Android malware use detection shunning techniques so as to cover their malicious activities from analysis tools. During this analysis, a brand-new detection and characterization system for investigation significant deviations within the network behaviour of a smart-phone application is planned. The most goal of the planned system is to guard mobile device users and cellular infrastructure corporations from malicious applications simply nine traffic feature measurements. The planned system isn’t solely ready to observe the malicious or masquerading apps, however may also determine them as general malware or specific malware (i.e. adware) on a mobile device. The planned methodology showed the common accuracy 94% for 5 classifiers namely; Random Forest (RF), K-Nearest Neighbour (KNN), decision Tree (DT), Random Tree (RT) and Regression (R) etc. We have a tendency to conjointly provide a tagged dataset of mobile malware traffic with a lot of applications includes benign and twelve completely different families of each adware and general malware. Recent substantial analysis on machine learning algorithms analyse options from mischievous application and use those preferences to catalogue and discover unknown malicious applications. This study condenses the progression of malware detection techniques supported machine learning algorithms centred on the Android Operating systems.

The rapid expansion of Android smartphones and their open-source characteristics have rendered them a primary target for malware attacks, endangering user privacy and device security. With the rise of malware attacks, robust and reliable security is not only wanted but much needed. As the Android malware landscape evolves, traditional approaches become increasingly challenging to implement with the same degree of accuracy in detecting new, emerging malware patterns. Recently, machine learning has gained attention as an effective and reliable solution in many application domains, including malware detection. However, traditional methods for detecting malware on Android smartphones are facing new challenges, such as a high false positive rate, performance problems, and a lack of scalability. In this study, we investigate the application of machine learning-based systematic practices to achieve effective and scalable Android malware detection. The experiments were conducted using a dataset consisting of over 15,000 benign and malicious Android apps. A SelectKBest feature selection method was used to reduce computation and improve efficiency by extracting the top 20 most relevant features. The extracted features were then used to train and validate four machine learning classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), and Multi-Layer Perceptron (MLP). The model was cross-validated using K-fold cross-validation to evaluate its performance on the entire dataset. Random Forest has achieved the highest accuracy among other models, which is 90.64%. The result demonstrates the feasibility of implementing static analysis feature selection and machine learning methods to improve the detection accuracy and computation efficiency. The study provides practical guidance for an optimized static analysis approach that focuses on manifest permissions, enhances detection accuracy, and reduces computational overhead for Android-based malware detection systems, thereby protecting mobile cybersecurity.

Android malware poses severe threats to users, hence raising an urgent demand for malware detection. In-cloud Android malware detection often suffers privacy leakage and communication overheads. Therefore, this article focuses on on-device Android malware detection. At present, on-device malware detectors are usually trained on servers and then transplanted to mobile devices (e.g., smartphones). In practice, on-device training is particularly important due to the demand for offline updates. Because mobile devices are limited in resource, however, on-device training is hard to implement, especially for those high-complexity malware detectors. To overcome this challenge, we design a lightweight on-device Android malware detector, based on the recently proposed broad learning method. Our detector mainly uses one-shot computation for model training. Hence it can be fully or incrementally trained directly on mobile devices. As far as detection accuracy is concerned, our detector outperforms the shallow learning-based models, including support vector machine (SVM) and AdaBoost, and approaches the deep learning-based models multilayer perceptron (MLP) and convolutional neural network (CNN). Moreover, our detector is more robust to adversarial examples than the existing detectors, and its robustness can be further improved through on-device model retraining. Finally, its advantages are confirmed by extensive experiments, and its practicality is demonstrated through runtime evaluation on smartphones.

Android OS is today the most used Operating System for mobile devices. However, it is susceptible to several malware attacks that may seriously compromise the privacy and security of individuals and organizations. This paper proposes an approach based on a static analysis of decompiled Android PacKages (APKs) to extract critical APIs and detect Android malware. The main contributions lie in the adoption of a graph-based data engineering schema to represent APIs taken from the Function Call Graphs of decompiled APKs and the formulation of a graph-based deep learning approach for explainable malware detection. In particular, the proposed approach, named , implements a Graph Neural Network (GNN) for binary classification (malware versus goodware), and integrates algorithm to disclose how specific API classes and control-flow edges between API calls influence malware alerts. The proposed approach was evaluated by considering 26,527 Android APKs. The results of an extensive and in-depth evaluation show that the presented GNN model achieves higher accuracy than deep neural models trained with traditional API call sequence representations and publicly available related methods. On the other hand, it produces decision explanations that yield interesting insights into the malicious patterns of APKs and support root cause analysis of missed malware alarms.

With the increase in the popularity of mobile devices, malicious applications targeting Android platform have greatly increased. Malware is coded so prudently that it has become very complicated to identify. The increase in the large amount of malware every day has made the manual approaches inadequate for detecting the malware. Nowadays, a new malware is characterized by sophisticated and complex obfuscation techniques. Thus, the static malware analysis alone is not enough for detecting it. However, dynamic malware analysis is appropriate to tackle evasion techniques but incapable to investigate all the execution paths and also it is very time consuming. So, for better detection and classification of Android malware, we propose a hybrid approach which integrates the features obtained after performing static and dynamic malware analysis. This approach tackles the problem of analyzing, detecting and classifying the Android malware in a more efficient manner. In this paper, we have used a robust set of features from static and dynamic malware analysis for creating two datasets i.e. binary and multiclass (family) classification datasets. These are made publically available on GitHub and Kaggle with the aim to help researchers and anti-malware tool creators for enhancing or developing new techniques and tools for detecting and classifying Android malware. Various machine learning algorithms are employed to detect and classify malware using the features extracted after performing static and dynamic malware analysis. The experimental outcomes indicate that hybrid approach enhances the accuracy of detection and classification of Android malware as compared to the case when static and dynamic features are considered alone.

EfficientNet convolutional neural networks-based Android malware detection

Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as system calls and permissions. However, recent findings have highlighted the fragility of such in-vitro evaluations with benchmark datasets, showing that very few changes to the content of Android malware may suffice to evade detection. How can we thus trust that a malware detector performing well on benchmark data will continue to do so when deployed in an operating environment? To mitigate this issue, the most popular Android malware detectors use linear, explainable machine-learning models to easily identify the most influential features contributing to each decision. In this work, we generalize this approach to any black-box machine- learning model, by leveraging a gradient-based approach to identify the most influential local features. This enables using nonlinear models to potentially increase accuracy without sacrificing interpretability of decisions. Our approach also highlights the global characteristics learned by the model to discriminate between benign and malware applications. Finally, as shown by our empirical analysis on a popular Android malware detection task, it also helps identifying potential vulnerabilities of linear and nonlinear models against adversarial manipulations.

With explosive growth of Android malware and due to the severity of its damages to smart phone users, the detection of Android malware has become increasingly important in cybersecurity. The increasing sophistication of Android malware calls for new defensive techniques that are capable against novel threats and harder to evade. In this paper, to detect Android malware, instead of using Application Programming Interface (API) calls only, we further analyze the different relationships between them and create higher-level semantics which require more effort for attackers to evade the detection. We represent the Android applications (apps), related APIs, and their rich relationships as a structured heterogeneous information network (HIN). Then we use a meta-path based approach to characterize the semantic relatedness of apps and APIs. We use each meta-path to formulate a similarity measure over Android apps, and aggregate different similarities using multi-kernel learning. Then each meta-path is automatically weighted by the learning algorithm to make predictions. To the best of our knowledge, this is the first work to use structured HIN for Android malware detection. Comprehensive experiments on real sample collections from Comodo Cloud Security Center are conducted to compare various malware detection approaches. Promising experimental results demonstrate that our developed system HinDroid outperforms other alternative Android malware detection techniques.

Over the past few years, Android Application is deemed as one of the fastest-growing technology areas. On the other hand, the rapid growth of android applications also increases the security threats for Android users in the form of malware. Malware hacks the personal information of a user and exploits it in different criminal activities. To date, various studies have been conducted for the detection of android malware. Some authors have preferred static analysis while others have performed dynamic analysis for android malware detection. In static analysis, researchers have only employed one feature of android application either intents or permissions. As best of our knowledge, there does not exist any technique that combines both intents and permissions. In this paper, we have performed static analysis for the detection of Android malware using android intents (both implicit and explicit), android permissions and combination of intents and permissions. Furthermore, the classification is performed to analyze the effectiveness of different machine learning algorithms for malware detection and to identify the best performing feature. Our experiment results show that combination of intents and permissions play a key role in the detection of android malware.

With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.

The increasing number of mobile devices using the Android operating system in the market makes these devices the first target for malicious applications. In recent years, several Android malware applications were developed to perform certain illegitimate activities and harmful actions on mobile devices. In response, specific tools and anti-virus programs used conventional signature-based methods in order to detect such Android malware applications. However, the most recent Android malware apps, such as zero-day, cannot be detected through conventional methods that are still based on fixed signatures or identifiers. Therefore, the most recently published research studies have suggested machine learning techniques as an alternative method to detect Android malware due to their ability to learn and use the existing information to detect the new Android malware apps. This paper presents the basic concepts of Android architecture, Android malware, and permission features utilized as effective malware predictors. Furthermore, a comprehensive review of the existing static, dynamic, and hybrid Android malware detection approaches is presented in this study. More significantly, this paper empirically discusses and compares the performances of six supervised machine learning algorithms, known as K-Nearest Neighbors (K-NN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and Logistic Regression (LR), which are commonly used in the literature for detecting malware apps.

While machine-learning algorithms have demonstrated a strong ability in detecting Android malware, they can be evaded by sparse evasion attacks crafted by injecting a small set of fake components, e.g., permissions and system calls, without compromising intrusive functionality. Previous work has shown that, to improve robustness against such attacks, learning algorithms should avoid overemphasizing few discriminant features, providing instead decisions that rely upon a large subset of components. In this work, we investigate whether gradient-based attribution methods, used to explain classifiers’ decisions by identifying the most relevant features, can be used to help identify and select more robust algorithms. To this end, we propose to exploit two different metrics that represent the evenness of explanations, and a new compact security measure called Adversarial Robustness Metric. Our experiments conducted on two different datasets and five classification algorithms for Android malware detection show that a strong connection exists between the uniformity of explanations and adversarial robustness. In particular, we found that popular techniques like Gradient*Input and Integrated Gradients are strongly correlated to security when applied to both linear and nonlinear detectors, while more elementary explanation techniques like the simple Gradient do not provide reliable information about the robustness of such classifiers.