The COVID-19 pandemic was a catalyst for many different trends in our daily life worldwide. While there has been an overall rise in cybercrime during this time, there has been relatively little research done about malicious COVID-19 themed AndroidOS applications. With the rise in reports of users falling victim to malicious COVID-19 themed AndroidOS applications, there is a need to learn about the detection of malware for pandemics-themed mobile apps.. In this project, we extracted the permissions requests from 1959 APK files from a dataset containing benign and malware COVID-19 themed apps. We then created and compared eight unique models of four varying classifiers to determine their ability to identify potentially malicious APK files based on the permissions the APK file requests: support vector machine, neural network, decision trees, and categorical naive bayes. These classifiers were then trained using Synthetic Minority Oversampling Technique (SMOTE) to balance the dataset due to the lack of samples of malware compared to non-malware APKs. Finally, we evaluated the models using K-Fold Cross-Validation and found the decision tree classifier to be the best performing classifier.
more »
« less
Identifying Android malware using network-based approaches
The proliferation of Android applications has resulted in many malicious apps entering the market and causing significant damage. Robust techniques that determine if an app is malicious are greatly needed. We propose the use of network-based approaches to effectively separate malicious from benign apps, based on a small labeled dataset. The apps in our dataset come from the Google Play Store and have been scanned for malicious behavior using VirusTotal to produce a ground truth dataset with labels malicious or benign. The apps in the resulting dataset have been represented in the form of binary feature vectors (where the features represent permissions, intent actions, discriminative APIs, obfuscation signatures, and native code signatures). We have used these vectors to build a weighted network that captures the “closeness” between apps. We propagate labels from the labeled apps to unlabeled apps, and evaluate the effectiveness of the approaches studied using the Fl-measure. We have conducted experiments to compare three variants of the label propagation approaches on datasets that consist of increasingly larger amounts of labeled data.
more »
« less
- NSF-PAR ID:
- 10163313
- Date Published:
- Journal Name:
- 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
- Page Range / eLocation ID:
- 903 to 906
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Machine learning-based malware detection systems are often vulnerable to evasion attacks, in which a malware developer manipulates their malicious software such that it is misclassified as benign. Such software hides some properties of the real class or adopts some properties of a different class by applying small perturbations. A special case of evasive malware hides by repackaging a bonafide benign mobile app to contain malware in addition to the original functionality of the app, thus retaining most of the benign properties of the original app. We present a novel malware detection system based on metamorphic testing principles that can detect such benign-seeming malware apps. We apply metamorphic testing to the feature representation of the mobile app, rather than to the app itself. That is, the source input is the original feature vector for the app and the derived input is that vector with selected features removed. If the app was originally classified benign, and is indeed benign, the output for the source and derived inputs should be the same class, i.e., benign, but if they differ, then the app is exposed as (likely) malware. Malware apps originally classified as malware should retain that classification, since only features prevalent in benign apps are removed. This approach enables the machine learning model to classify repackaged malware with reasonably few false negatives and false positives. Our training pipeline is simpler than many existing ML-based malware detection methods, as the network is trained end-to-end to jointly learn appropriate features and to perform classification. We pre-trained our classifier model on 3 million apps collected from the widely-used AndroZoo dataset. 1 We perform an extensive study on other publicly available datasets to show our approach’s effectiveness in detecting repackaged malware with more than 94% accuracy, 0.98 precision, 0.95 recall, and 0.96 F1 score.more » « less
-
null (Ed.)In recent years, enterprises have been targeted by advanced adversaries who leverage creative ways to infiltrate their systems and move laterally to gain access to critical data. One increasingly common evasive method is to hide the malicious activity behind a benign program by using tools that are already installed on user computers. These programs are usually part of the operating system distribution or another user-installed binary, therefore this type of attack is called “Living-Off-The-Land”. Detecting these attacks is challenging, as adversaries may not create malicious files on the victim computers and anti-virus scans fail to detect them. We propose the design of an Active Learning framework called LOLAL for detecting Living-Off-the-Land attacks that iteratively selects a set of uncertain and anomalous samples for labeling by a human analyst. LOLAL is specifically designed to work well when a limited number of labeled samples are available for training machine learning models to detect attacks. We investigate methods to represent command-line text using word-embedding techniques, and design ensemble boosting classifiers to distinguish malicious and benign samples based on the embedding representation. We leverage a large, anonymized dataset collected by an endpoint security product and demonstrate that our ensemble classifiers achieve an average F1 score of 96% at classifying different attack classes. We show that our active learning method consistently improves the classifier performance, as more training data is labeled, and converges in less than 30 iterations when starting with a small number of labeled instances.more » « less
-
null (Ed.)Android is the most targeted mobile OS. Studies have found that repackaging is one of the most common techniques that adversaries use to distribute malware, and detecting such malware can be difficult because they share large parts of the code with benign apps. Other studies have highlighted the privacy implications of zero-permission sensors. In this work, we investigate if repackaged malicious apps utilize more sensors than the benign counterpart for malicious purposes. We analyzed 15,297 app pairs for sensor usage. We provide evidence that zero-permission sensors are indeed used by malicious apps to perform various activities. We use this information to train a robust classifier to detect repackaged malware in the wild.more » « less
-
null (Ed.)Network intrusion detection systems (IDS) has efficiently identified the profiles of normal network activities, extracted intrusion patterns, and constructed generalized models to evaluate (un)known attacks using a wide range of machine learning approaches. In spite of the effectiveness of machine learning-based IDS, it has been still challenging to reduce high false alarms due to data misclassification. In this paper, by using multiple decision mechanisms, we propose a new classification method to identify misclassified data and then to classify them into three different classes, called a malicious, benign, and ambiguous dataset. In other words, the ambiguous dataset contains a majority of the misclassified dataset and is thus the most informative for improving the model and anomaly detection because of the lack of confidence for the data classification in the model. We evaluate our approach with the recent real-world network traffic data, Kyoto2006+ datasets, and show that the ambiguous dataset contains 77.2% of the previously misclassified data. Re-evaluating the ambiguous dataset effectively reduces the false prediction rate with minimal overhead and improves accuracy by 15%.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3341161.3343534
