An integrated malware detection and classification system

This thesis is to develop effective and efficient methodologies which can be applied to continuously improve the performance of detection and classification on malware collected over an extended period of time. The robustness of the proposed methodologies has been tested on malware collected over 2003-2010.

A comparison of the classification of disparate malware collected in different time periods

It has been argued that an anti-virus strategy based on malware collected at a certain date, will not work at a later date because malware evolves rapidly and an anti-virus engine is then faced with a completely new type of executable not as amenable to detection as the first was.

In this paper, we test this idea by collecting two sets of malware, the first from 2002 to 2007, the second from 2009 to 2010 to determine how well the anti-virus strategy we developed based on the earlier set [18] will do on the later set. This anti-virus strategy integrates dynamic and static features extracted from the executables to classify malware by distinguishing between families. We also perform another test, to investigate the same idea whereby we accumulate all the malware executables in the old and new dataset, separately, and apply a malware versus cleanware classification.

The resulting classification accuracies are very close for both datasets, with a difference of approximately 5.4% for both experiments, the older malware being more accurately classified than the newer malware. This leads us to conjecture that current anti-virus strategies can indeed be modified to deal effectively with new malware.

Malware distributed collection and pre-classification system using honeypot technology

Malware has become a major threat in the last years due to the ease of spread through the Internet. Malware detection has become difficult with the use of compression, polymorphic methods and techniques to detect and disable security software. Those and other obfuscation techniques pose a problem for detection and classification schemes that analyze malware behavior. In this paper we propose a distributed architecture to improve malware collection using different honeypot technologies to increase the variety of malware collected. We also present a daemon tool developed to grab malware distributed through spam and a pre-classification technique that uses antivirus technology to separate malware in generic classes. © 2009 SPIE.

Android Malware Detection Using Parallel Machine Learning Classifiers

Mobile malware has continued to grow at an alarming rate despite on-going mitigation efforts. This has been much more prevalent on Android due to being an open platform that is rapidly overtaking other competing platforms in the mobile smart devices market. Recently, a new generation of Android malware families has emerged with advanced evasion capabilities which make them much more difficult to detect using conventional methods. This paper proposes and investigates a parallel machine learning based classification approach for early detection of Android malware. Using real malware samples and benign applications, a composite classification model is developed from parallel combination of heterogeneous classifiers. The empirical evaluation of the model under different combination schemes demonstrates its efficacy and potential to improve detection accuracy. More importantly, by utilizing several classifiers with diverse characteristics, their strengths can be harnessed not only for enhanced Android malware detection but also quicker white box analysis by means of the more interpretable constituent classifiers.

Malware detection: program run length against detection rate

N-gram analysis is an approach that investigates the structure of a program using bytes, characters or text strings. This research uses dynamic analysis to investigate malware detection using a classification approach based on N-gram analysis. A key issue with dynamic analysis is the length of time a program has to be run to ensure a correct classification. The motivation for this research is to find the optimum subset of operational codes (opcodes) that make the best indicators of malware and to determine how long a program has to be monitored to ensure an accurate support vector machine (SVM) classification of benign and malicious software. The experiments within this study represent programs as opcode density histograms gained through dynamic analysis for different program run periods. A SVM is used as the program classifier to determine the ability of different program run lengths to correctly determine the presence of malicious software. The findings show that malware can be detected with different program run lengths using a small number of opcodes

N-gram density based malware detection

N-gram analysis is an approach that investigates the structure of a program using bytes, characters or text strings. This research uses dynamic analysis to investigate malware detection using a classification approach based on N-gram analysis. The motivation for this research is to find a subset of Ngram features that makes a robust indicator of malware. The experiments within this paper represent programs as N-gram density histograms, gained through dynamic analysis. A Support Vector Machine (SVM) is used as the program classifier to determine the ability of N-grams to correctly determine the presence of malicious software. The preliminary findings show that an N-gram size N=3 and N=4 present the best avenues for further analysis.

Detecting obfuscated malware using reduced opcode set and optimised runtime trace

The research presented, investigates the optimal set of operational codes (opcodes) that create a robust indicator of malicious software (malware) and also determines a program’s execution duration for accurate classification of benign and malicious software. The features extracted from the dataset are opcode density histograms, extracted during the program execution. The classifier used is a support vector machine and is configured to select those features to produce the optimal classification of malware over different program run lengths. The findings demonstrate that malware can be detected using dynamic analysis with relatively few opcodes.

Differentiating malware from cleanware using behavioural analysis

This paper proposes a scalable approach for distinguishing malicious files from clean files by investigating the behavioural features using logs of various API calls. We also propose, as an alternative to the traditional method of manually identifying malware files, an automated classification system using runtime features of malware files. For both projects, we use an automated tool running in a virtual environment to extract API call features from executables and apply pattern recognition algorithms and statistical methods to differentiate between files. Our experimental results, based on a dataset of 1368 malware and 456 cleanware files, provide an accuracy of over 97% in distinguishing malware from cleanware. Our techniques provide a similar accuracy for classifying malware into families. In both cases, our results outperform comparable previously published techniques.

Android malware detection with contrasting permission patterns

As the risk of malware is sharply increasing in Android platform, Android malware detection has become an important research topic. Existing works have demonstrated that required permissions of Android applications are valuable for malware analysis, but how to exploit those permission patterns for malware detection remains an open issue. In this paper, we introduce the contrasting permission patterns to characterize the essential differences between malwares and clean applications from the permission aspect. Then a framework based on contrasting permission patterns is presented for Android malware detection. According to the proposed framework, an ensemble classifier, Enclamald, is further developed to detect whether an application is potentially malicious. Every contrasting permission pattern is acting as a weak classifier in Enclamald, and the weighted predictions of involved weak classifiers are aggregated to the final result. Experiments on real-world applications validate that the proposed Enclamald classifier outperforms commonly used classifiers for Android Malware Detection.

Multi-dimensional classification using Bayesian networks for stationary and evolving streaming data

Hoy en día, con la evolución continua y rápida de las tecnologías de la información y los dispositivos de computación, se recogen y almacenan continuamente grandes volúmenes de datos en distintos dominios y a través de diversas aplicaciones del mundo real. La extracción de conocimiento útil de una cantidad tan enorme de datos no se puede realizar habitualmente de forma manual, y requiere el uso de técnicas adecuadas de aprendizaje automático y de minería de datos. La clasificación es una de las técnicas más importantes que ha sido aplicada con éxito a varias áreas. En general, la clasificación se compone de dos pasos principales: en primer lugar, aprender un modelo de clasificación o clasificador a partir de un conjunto de datos de entrenamiento, y en segundo lugar, clasificar las nuevas instancias de datos utilizando el clasificador aprendido. La clasificación es supervisada cuando todas las etiquetas están presentes en los datos de entrenamiento (es decir, datos completamente etiquetados), semi-supervisada cuando sólo algunas etiquetas son conocidas (es decir, datos parcialmente etiquetados), y no supervisada cuando todas las etiquetas están ausentes en los datos de entrenamiento (es decir, datos no etiquetados). Además, aparte de esta taxonomía, el problema de clasificación se puede categorizar en unidimensional o multidimensional en función del número de variables clase, una o más, respectivamente; o también puede ser categorizado en estacionario o cambiante con el tiempo en función de las características de los datos y de la tasa de cambio subyacente. A lo largo de esta tesis, tratamos el problema de clasificación desde tres perspectivas diferentes, a saber, clasificación supervisada multidimensional estacionaria, clasificación semisupervisada unidimensional cambiante con el tiempo, y clasificación supervisada multidimensional cambiante con el tiempo. Para llevar a cabo esta tarea, hemos usado básicamente los clasificadores Bayesianos como modelos. La primera contribución, dirigiéndose al problema de clasificación supervisada multidimensional estacionaria, se compone de dos nuevos métodos de aprendizaje de clasificadores Bayesianos multidimensionales a partir de datos estacionarios. Los métodos se proponen desde dos puntos de vista diferentes. El primer método, denominado CB-MBC, se basa en una estrategia de envoltura de selección de variables que es voraz y hacia delante, mientras que el segundo, denominado MB-MBC, es una estrategia de filtrado de variables con una aproximación basada en restricciones y en el manto de Markov. Ambos métodos han sido aplicados a dos problemas reales importantes, a saber, la predicción de los inhibidores de la transcriptasa inversa y de la proteasa para el problema de infección por el virus de la inmunodeficiencia humana tipo 1 (HIV-1), y la predicción del European Quality of Life-5 Dimensions (EQ-5D) a partir de los cuestionarios de la enfermedad de Parkinson con 39 ítems (PDQ-39). El estudio experimental incluye comparaciones de CB-MBC y MB-MBC con los métodos del estado del arte de la clasificación multidimensional, así como con métodos comúnmente utilizados para resolver el problema de predicción de la enfermedad de Parkinson, a saber, la regresión logística multinomial, mínimos cuadrados ordinarios, y mínimas desviaciones absolutas censuradas. En ambas aplicaciones, los resultados han sido prometedores con respecto a la precisión de la clasificación, así como en relación al análisis de las estructuras gráficas que identifican interacciones conocidas y novedosas entre las variables. La segunda contribución, referida al problema de clasificación semi-supervisada unidimensional cambiante con el tiempo, consiste en un método nuevo (CPL-DS) para clasificar flujos de datos parcialmente etiquetados. Los flujos de datos difieren de los conjuntos de datos estacionarios en su proceso de generación muy rápido y en su aspecto de cambio de concepto. Es decir, los conceptos aprendidos y/o la distribución subyacente están probablemente cambiando y evolucionando en el tiempo, lo que hace que el modelo de clasificación actual sea obsoleto y deba ser actualizado. CPL-DS utiliza la divergencia de Kullback-Leibler y el método de bootstrapping para cuantificar y detectar tres tipos posibles de cambio: en las predictoras, en la a posteriori de la clase o en ambas. Después, si se detecta cualquier cambio, un nuevo modelo de clasificación se aprende usando el algoritmo EM; si no, el modelo de clasificación actual se mantiene sin modificaciones. CPL-DS es general, ya que puede ser aplicado a varios modelos de clasificación. Usando dos modelos diferentes, el clasificador naive Bayes y la regresión logística, CPL-DS se ha probado con flujos de datos sintéticos y también se ha aplicado al problema real de la detección de código malware, en el cual los nuevos ficheros recibidos deben ser continuamente clasificados en malware o goodware. Los resultados experimentales muestran que nuestro método es efectivo para la detección de diferentes tipos de cambio a partir de los flujos de datos parcialmente etiquetados y también tiene una buena precisión de la clasificación. Finalmente, la tercera contribución, sobre el problema de clasificación supervisada multidimensional cambiante con el tiempo, consiste en dos métodos adaptativos, a saber, Locally Adpative-MB-MBC (LA-MB-MBC) y Globally Adpative-MB-MBC (GA-MB-MBC). Ambos métodos monitorizan el cambio de concepto a lo largo del tiempo utilizando la log-verosimilitud media como métrica y el test de Page-Hinkley. Luego, si se detecta un cambio de concepto, LA-MB-MBC adapta el actual clasificador Bayesiano multidimensional localmente alrededor de cada nodo cambiado, mientras que GA-MB-MBC aprende un nuevo clasificador Bayesiano multidimensional. El estudio experimental realizado usando flujos de datos sintéticos multidimensionales indica los méritos de los métodos adaptativos propuestos. ABSTRACT Nowadays, with the ongoing and rapid evolution of information technology and computing devices, large volumes of data are continuously collected and stored in different domains and through various real-world applications. Extracting useful knowledge from such a huge amount of data usually cannot be performed manually, and requires the use of adequate machine learning and data mining techniques. Classification is one of the most important techniques that has been successfully applied to several areas. Roughly speaking, classification consists of two main steps: first, learn a classification model or classifier from an available training data, and secondly, classify the new incoming unseen data instances using the learned classifier. Classification is supervised when the whole class values are present in the training data (i.e., fully labeled data), semi-supervised when only some class values are known (i.e., partially labeled data), and unsupervised when the whole class values are missing in the training data (i.e., unlabeled data). In addition, besides this taxonomy, the classification problem can be categorized into uni-dimensional or multi-dimensional depending on the number of class variables, one or more, respectively; or can be also categorized into stationary or streaming depending on the characteristics of the data and the rate of change underlying it. Through this thesis, we deal with the classification problem under three different settings, namely, supervised multi-dimensional stationary classification, semi-supervised unidimensional streaming classification, and supervised multi-dimensional streaming classification. To accomplish this task, we basically used Bayesian network classifiers as models. The first contribution, addressing the supervised multi-dimensional stationary classification problem, consists of two new methods for learning multi-dimensional Bayesian network classifiers from stationary data. They are proposed from two different points of view. The first method, named CB-MBC, is based on a wrapper greedy forward selection approach, while the second one, named MB-MBC, is a filter constraint-based approach based on Markov blankets. Both methods are applied to two important real-world problems, namely, the prediction of the human immunodeficiency virus type 1 (HIV-1) reverse transcriptase and protease inhibitors, and the prediction of the European Quality of Life-5 Dimensions (EQ-5D) from 39-item Parkinson’s Disease Questionnaire (PDQ-39). The experimental study includes comparisons of CB-MBC and MB-MBC against state-of-the-art multi-dimensional classification methods, as well as against commonly used methods for solving the Parkinson’s disease prediction problem, namely, multinomial logistic regression, ordinary least squares, and censored least absolute deviations. For both considered case studies, results are promising in terms of classification accuracy as well as regarding the analysis of the learned MBC graphical structures identifying known and novel interactions among variables. The second contribution, addressing the semi-supervised uni-dimensional streaming classification problem, consists of a novel method (CPL-DS) for classifying partially labeled data streams. Data streams differ from the stationary data sets by their highly rapid generation process and their concept-drifting aspect. That is, the learned concepts and/or the underlying distribution are likely changing and evolving over time, which makes the current classification model out-of-date requiring to be updated. CPL-DS uses the Kullback-Leibler divergence and bootstrapping method to quantify and detect three possible kinds of drift: feature, conditional or dual. Then, if any occurs, a new classification model is learned using the expectation-maximization algorithm; otherwise, the current classification model is kept unchanged. CPL-DS is general as it can be applied to several classification models. Using two different models, namely, naive Bayes classifier and logistic regression, CPL-DS is tested with synthetic data streams and applied to the real-world problem of malware detection, where the new received files should be continuously classified into malware or goodware. Experimental results show that our approach is effective for detecting different kinds of drift from partially labeled data streams, as well as having a good classification performance. Finally, the third contribution, addressing the supervised multi-dimensional streaming classification problem, consists of two adaptive methods, namely, Locally Adaptive-MB-MBC (LA-MB-MBC) and Globally Adaptive-MB-MBC (GA-MB-MBC). Both methods monitor the concept drift over time using the average log-likelihood score and the Page-Hinkley test. Then, if a drift is detected, LA-MB-MBC adapts the current multi-dimensional Bayesian network classifier locally around each changed node, whereas GA-MB-MBC learns a new multi-dimensional Bayesian network classifier from scratch. Experimental study carried out using synthetic multi-dimensional data streams shows the merits of both proposed adaptive methods.

Análisis de características estáticas de ficheros ejecutables para la clasificación de Malware

El Malware es una grave amenaza para la seguridad de los sistemas. Con el uso generalizado de la World Wide Web, ha habido un enorme aumento en los ataques de virus, haciendo que la seguridad informática sea esencial para todas las computadoras y se expandan las áreas de investigación sobre los nuevos incidentes que se generan, siendo una de éstas la clasificación del malware. Los “desarrolladores de malware” utilizan nuevas técnicas para generar malware polimórfico reutilizando los malware existentes, por lo cual es necesario agruparlos en familias para estudiar sus características y poder detectar nuevas variantes de los mismos. Este trabajo, además de presentar un detallado estado de la cuestión de la clasificación del malware de ficheros ejecutables PE, presenta un enfoque en el que se mejora el índice de la clasificación de la base de datos de Malware MALICIA utilizando las características estáticas de ficheros ejecutables Imphash y Pehash, utilizando dichas características se realiza un clustering con el algoritmo clustering agresivo el cual se cambia con la clasificación actual mediante el algoritmo de majority voting y la característica icon_label, obteniendo un Precision de 99,15% y un Recall de 99,32% mejorando la clasificación de MALICIA con un F-measure de 99,23%.---ABSTRACT---Malware is a serious threat to the security of systems. With the widespread use of the World Wide Web, there has been a huge increase in virus attacks, making the computer security essential for all computers. Near areas of research have append in this area including classifying malware into families, Malware developers use polymorphism to generate new variants of existing malware. Thus it is crucial to group variants of the same family, to study their characteristics and to detect new variants. This work, in addition to presenting a detailed analysis of the problem of classifying malware PE executable files, presents an approach in which the classification in the Malware database MALICIA is improved by using static characteristics of executable files, namely Imphash and Pehash. Both features are evaluated through clustering real malware with family labels with aggressive clustering algorithm and combining this with the current classification by Majority voting algorithm, obtaining a Precision of 99.15% and a Recall of 99.32%, improving the classification of MALICIA with an F-measure of 99,23%.

A fast malware feature selection approach using a hybrid of multi-linear and stepwise binary logistic regression

Malware replicates itself and produces offspring with the same characteristics but different signatures by using code obfuscation techniques. Current generation anti-virus engines employ a signature-template type detection approach where malware can easily evade existing signatures in the database. This reduces the capability of current anti-virus engines in detecting malware. In this paper, we propose a stepwise binary logistic regression-based dimensionality reduction techniques for malware detection using application program interface (API) call statistics. Finding the most significant malware feature using traditional wrapper-based approaches takes an exponential complexity of the dimension (m) of the dataset with a brute-force search strategies and order of (m-1) complexity with a backward elimination filter heuristics. The novelty of the proposed approach is that it finds the worst case computational complexity which is less than order of (m-1). The proposed approach uses multi-linear regression and the p-value of each individual API feature for selection of the most uncorrelated and significant features in order to reduce the dimensionality of the large malware data and to ensure the absence of multi-collinearity. The stepwise logistic regression approach is then employed to test the significance of the individual malware feature based on their corresponding Wald statistic and to construct the binary decision the model. When the selected most significant APIs are used in a decision rule generation systems, this approach not only reduces the tree size but also improves classification performance. Exhaustive experiments on a large malware data set show that the proposed approach clearly exceeds the existing standard decision rule, support vector machine-based template approach with complete data and provides a better statistical fitness.