Modern computing systems have led cyber adversaries to create more sophisticated malware than was previously available in the early days of technology. Dated detection techniques such as Anti-Virus Software (AVS) based on signature-based methods could no longer keep up with the demand that computer systems required of them. The complexity of modern malware has led to the development of contemporary detection techniques that use the machine learning field and hardware to boost the detection rates of malicious software. These new techniques use Hardware Performance Counters (HPCs) that form a digital signature of sorts. After the models are fed training data, they can reference these HPCs to classify zero-day malware samples. A problem emerges when malware with no comparable HPC values comes into contact with these new techniques. We provide an analysis of several machine learning and deep learning models that run zero-day samples and evaluate the results from the conversion of C++ algorithms to a hardware description language (HDL) used to begin a hardware implementation. Our results present a lack of accuracy from the models when running zero-day malware data as our highest detector, decision tree, was only able to reach 91.2% accuracy and had an F1-Score of 91.5% in the form of a decision tree. Next, through the Receiver Operating Curve (ROC) and area-under-the-curve (AUC), we can also determine that the algorithms did not present significant robustness as the largest AUC was only 0.819. In addition, we viewed relatively high overhead for our ensemble learning algorithm while also only having an 86.3% accuracy and 86% F1-Score. Finally, as an additional task, we adapted the one rule algorithm to fit many rules to make malware classification understandable to everyday users by allowing them to view the regulations while maintaining relatively high accuracy.
Network and system security are incredibly critical issues now. Due to the rapid proliferation of malware, traditional analysis methods struggle with enormous samples. In this paper, we propose four easy-to-extract and small-scale features, including sizes and permissions of Windows PE sections, content complexity, and import libraries, to classify malware families, and use automatic machine learning to search for the best model and hyper-parameters for each feature and their combinations. Compared with detailed behavior-related features like API sequences, proposed features provide macroscopic information about malware. The analysis is based on static disassembly scripts and hexadecimal machine code. Unlike dynamic behavior analysis, static analysis is resource-efficient and offers complete code coverage, but is vulnerable to code obfuscation and encryption. The results demonstrate that features which work well in dynamic analysis are not necessarily effective when applied to static analysis. For instance, API 4-grams only achieve 57.96% accuracy and involve a relatively high dimensional feature set (5000 dimensions). In contrast, the novel proposed features together with a classical machine learning algorithm (Random Forest) presents very good accuracy at 99.40% and the feature vector is of much smaller dimension (40 dimensions). We demonstrate the effectiveness of this approach through integration in IDA Pro, which also facilitates the collection of new training samples and subsequent model retraining.
This paper presents a new Android malware detection method based on Graph Neural Networks (GNNs) with Jumping-Knowledge (JK). Android function call graphs (FCGs) consist of a set of program functions and their inter-procedural calls. Thus, this paper proposes a GNN-based method for Android malware detection by capturing meaningful intra-procedural call path patterns. In addition, a Jumping-Knowledge technique is applied to minimize the effect of the over-smoothing problem, which is common in GNNs. The proposed method has been extensively evaluated using two benchmark datasets. The results demonstrate the superiority of our approach compared to state-of-the-art approaches in terms of key classification metrics, which demonstrates the potential of GNNs in Android malware detection and classification.
Classification of malware families is crucial for a comprehensive understanding of how they can infect devices, computers, or systems. Thus, malware identification enables security researchers and incident responders to take precautions against malware and accelerate mitigation. API call sequences made by malware are widely utilized features by machine and deep learning models for malware classification as these sequences represent the behavior of malware. However, traditional machine and deep learning models remain incapable of capturing sequence relationships between API calls. On the other hand, the transformer-based models process sequences as a whole and learn relationships between API calls due to multi-head attention mechanisms and positional embeddings. Our experiments demonstrate that the transformer model with one transformer block layer surpassed the widely used base architecture, LSTM. Moreover, BERT or CANINE, pre-trained transformer models, outperformed in classifying highly imbalanced malware families according to evaluation metrics, F1-score, and AUC score. Furthermore, the proposed bagging-based random transformer forest (RTF), an ensemble of BERT or CANINE, has reached the state-of-the-art evaluation scores on three out of four datasets, particularly state-of-the-art F1-score of 0.6149 on one of the commonly used benchmark dataset.
Nowadays, malware and malware incidents are increasing daily, even with various antivirus systems and malware detection or classification methodologies. Machine learning techniques have been the main focus of the security experts to detect malware and determine their families. Many static, dynamic, and hybrid techniques have been presented for that purpose. In this study, the static analysis technique has been applied to malware samples to extract API calls, which is one of the most used features in machine/deep learning models as it represents the behavior of malware samples. Since the rapid increase and continuous evolution of malware affect the detection capacity of antivirus scanners, recent and updated datasets of malicious software became necessary to overcome this drawback. This paper introduces two new datasets: One with 14,616 samples obtained and compiled from VirusShare and one with 9,795 samples from VirusSample. In addition, benchmark results based on static API calls of malware samples are presented using several machine and deep learning models on these datasets. We believe that these two datasets and benchmark results enable researchers to test and validate their methods and approaches in this field.
Driven by the high profit, Portable Executable (PE) malware has been consistently evolving in terms of both volume and sophistication. PE malware family classification has gained great attention and a large number of approaches have been proposed. With the rapid development of machine learning techniques and the exciting results they achieved on various tasks, machine learning algorithms have also gained popularity in the PE malware family classification task. Three mainstream approaches that use learning based algorithms, as categorized by the input format the methods take, are image-based, binary-based and disassembly-based approaches. Although a large number of approaches are published, there is no consistent comparisons on those approaches, especially from the practical industry adoption perspective. Moreover, there is no comparison in the scenario of concept drift, which is a fact for the malware classification task due to the fast evolving nature of malware. In this work, we conduct a thorough empirical study on learning-based PE malware classification approaches on 4 different datasets and consistent experiment settings. Based on the experiment results and an interview with our industry partners, we find that (1) there is no individual class of methods that significantly outperforms the others; (2) All classes of methods show performance degradation on concept drift (by an average F1-score of 32.23%); and (3) the prediction time and high memory consumption hinder existing approaches from being adopted for industry usage.
In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing defenses, by tracing back a successful attack to its root cause, and offering a path forward for mitigation to prevent similar attacks in the future. In this paper, we describe our efforts in developing a forensic traceback tool for poison attacks on deep neural networks. We propose a novel iterative clustering and pruning solution that trims "innocent" training samples, until all that remains is the set of poisoned data responsible for the attack. Our method clusters training samples based on their impact on model parameters, then uses an efficient data unlearning method to prune innocent clusters. We empirically demonstrate the efficacy of our system on three types of dirty-label (backdoor) poison attacks and three types of clean-label poison attacks, across domains of computer vision and malware classification. Our system achieves over 98.4% precision and 96.8% recall across all attacks. We also show that our system is robust against four anti-forensics measures specifically designed to attack it.
Supervised Deep Learning requires plenty of labeled data to converge, and hence perform optimally for task-specific learning. Therefore, we propose a novel mechanism named DRo (for Deep Routing) for data-scarce domains like security. The DRo approach builds upon some of the recent developments in Deep-Clustering. In particular, it exploits the self-augmented training mechanism using synthetically generated local perturbations. DRo not only allays the challenges with sparse-labeled data but also offers many unique advantages. We also developed a system named DRoID that uses the DRo mechanism for enhancing the performance of an existing Malware Detection System that uses (low information features like the) Android implicit Intent(s) as the only features. We conduct experiments on DRoID using a popular and standardized Android malware dataset and found that the DRo mechanism could successfully reduce the false-alarms generated by the downstream classifier by 67.9%, and also simultaneously boosts its accuracy by 11.3%. This is significant not only because the gains achieved are unparalleled but also because the features used were never considered rich enough to train a classifier on; and hence no decent performance could ever be reported by any malware classification system till-date using these features in isolation. Owing to the results achieved, the DRo mechanism claims a dominant position amongst all known systems that aims to enhance the classification performance of deep learning models with sparse-labeled data.
With the rapid growth of the number of devices on the Internet, malware poses a threat not only to the affected devices but also their ability to use said devices to launch attacks on the Internet ecosystem. Rapid malware classification is an important tools to combat that threat. One of the successful approaches to classification is based on malware images and deep learning. While many deep learning architectures are very accurate they usually take a long time to train. In this work we perform experiments on multiple well known, pre-trained, deep network architectures in the context of transfer learning. We show that almost all them classify malware accurately with a very short training period.
Malicious activities in cyberspace have gone further than simply hacking machines and spreading viruses. It has become a challenge for a nations survival and hence has evolved to cyber warfare. Malware is a key component of cyber-crime, and its analysis is the first line of defence against attack. This work proposes a novel deep boosted hybrid learning-based malware classification framework and named as Deep boosted Feature Space-based Malware classification (DFS-MC). In the proposed framework, the discrimination power is enhanced by fusing the feature spaces of the best performing customized CNN architectures models and its discrimination by an SVM for classification. The discrimination capacity of the proposed classification framework is assessed by comparing it against the standard customized CNNs. The customized CNN models are implemented in two ways: softmax classifier and deep hybrid learning-based malware classification. In the hybrid learning, Deep features are extracted from customized CNN architectures and fed into the conventional machine learning classifier to improve the classification performance. We also introduced the concept of transfer learning in a customized CNN architecture based malware classification framework through fine-tuning. The performance of the proposed malware classification approaches are validated on the MalImg malware dataset using the hold-out cross-validation technique. Experimental comparisons were conducted by employing innovative, customized CNN, trained from scratch and fine-tuning the customized CNN using transfer learning. The proposed classification framework DFS-MC showed improved results, Accuracy: 98.61%, F-score: 0.96, Precision: 0.96, and Recall: 0.96.
In this paper we study data augmentation for opcode sequence based Android malware detection. Data augmentation has been successfully used in many areas of deep-learning to significantly improve model performance. Typically, data augmentation simulates realistic variations in data to increase the apparent diversity of the training-set. However, for opcode-based malware analysis it is not immediately clear how to apply data augmentation. Hence we first study the use of fixed transformations, then progress to adaptive methods. We propose a novel data augmentation method -- Self-Embedding Language Model Augmentation -- that uses a malware detection network's own opcode embedding layer to measure opcode similarity for adaptive augmentation. To the best of our knowledge this is the first paper to carry out a systematic study of different augmentation methods for opcode sequence based Android malware classification.
Research in the field of malware classification often relies on machine learning models that are trained on high-level features, such as opcodes, function calls, and control flow graphs. Extracting such features is costly, since disassembly or code execution is generally required. In this paper, we conduct experiments to train and evaluate machine learning models for malware classification, based on features that can be obtained without disassembly or execution of code. Specifically, we visualize malware samples as images and employ image analysis techniques. In this context, we focus on two machine learning models, namely, Convolutional Neural Networks (CNN) and Extreme Learning Machines (ELM). Surprisingly, we find that ELMs can achieve accuracies on par with CNNs, yet ELM training requires less than~2\%\ of the time needed to train a comparable CNN.
In this paper, we consider malware classification using deep learning techniques and image-based features. We employ a wide variety of deep learning techniques, including multilayer perceptrons (MLP), convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent units (GRU). Amongst our CNN experiments, transfer learning plays a prominent role specifically, we test the VGG-19 and ResNet152 models. As compared to previous work, the results presented in this paper are based on a larger and more diverse malware dataset, we consider a wider array of features, and we experiment with a much greater variety of learning techniques. Consequently, our results are the most comprehensive and complete that have yet been published.
Word embeddings are often used in natural language processing as a means to quantify relationships between words. More generally, these same word embedding techniques can be used to quantify relationships between features. In this paper, we first consider multiple different word embedding techniques within the context of malware classification. We use hidden Markov models to obtain embedding vectors in an approach that we refer to as HMM2Vec, and we generate vector embeddings based on principal component analysis. We also consider the popular neural network based word embedding technique known as Word2Vec. In each case, we derive feature embeddings based on opcode sequences for malware samples from a variety of different families. We show that we can obtain better classification accuracy based on these feature embeddings, as compared to HMM experiments that directly use the opcode sequences, and serve to establish a baseline. These results show that word embeddings can be a useful feature engineering step in the field of malware analysis.
Malicious applications (particularly those targeting the Android platform) pose a serious threat to developers and end-users. Numerous research efforts have been devoted to developing effective approaches to defend against Android malware. However, given the explosive growth of Android malware and the continuous advancement of malicious evasion technologies like obfuscation and reflection, Android malware defense approaches based on manual rules or traditional machine learning may not be effective. In recent years, a dominant research field called deep learning (DL), which provides a powerful feature abstraction ability, has demonstrated a compelling and promising performance in a variety of areas, like natural language processing and computer vision. To this end, employing deep learning techniques to thwart Android malware attacks has recently garnered considerable research attention. Yet, no systematic literature review focusing on deep learning approaches for Android Malware defenses exists. In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment. As a result, a total of 132 studies covering the period 2014-2021 were identified. Our investigation reveals that, while the majority of these sources mainly consider DL-based on Android malware detection, 53 primary studies (40.1 percent) design defense approaches based on other scenarios. This review also discusses research trends, research focuses, challenges, and future research directions in DL-based Android malware defenses.
Discrete hidden Markov models (HMM) are often applied to malware detection and classification problems. However, the continuous analog of discrete HMMs, that is, Gaussian mixture model-HMMs (GMM-HMM), are rarely considered in the field of cybersecurity. In this paper, we use GMM-HMMs for malware classification and we compare our results to those obtained using discrete HMMs. As features, we consider opcode sequences and entropy-based sequences. For our opcode features, GMM-HMMs produce results that are comparable to those obtained using discrete HMMs, whereas for our entropy-based features, GMM-HMMs generally improve significantly on the classification results that we have achieved with discrete HMMs.
Signature and anomaly based techniques are the quintessential approaches to malware detection. However, these techniques have become increasingly ineffective as malware has become more sophisticated and complex. Researchers have therefore turned to deep learning to construct better performing model. In this paper, we create four different long-short term memory (LSTM) based models and train each to classify malware samples from 20 families. Our features consist of opcodes extracted from malware executables. We employ techniques used in natural language processing (NLP), including word embedding and bidirection LSTMs (biLSTM), and we also use convolutional neural networks (CNN). We find that a model consisting of word embedding, biLSTMs, and CNN layers performs best in our malware classification experiments.
Malware classification is an important and challenging problem in information security. Modern malware classification techniques rely on machine learning models that can be trained on features such as opcode sequences, API calls, and byte $n$-grams, among many others. In this research, we consider opcode features. We implement hybrid machine learning techniques, where we engineer feature vectors by training hidden Markov models -- a technique that we refer to as HMM2Vec -- and Word2Vec embeddings on these opcode sequences. The resulting HMM2Vec and Word2Vec embedding vectors are then used as features for classification algorithms. Specifically, we consider support vector machine (SVM), $k$-nearest neighbor ($k$-NN), random forest (RF), and convolutional neural network (CNN) classifiers. We conduct substantial experiments over a variety of malware families. Our experiments extend well beyond any previous work in this field.
Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs) with small uniform norm-bounded perturbations across features to maintain the requirement of imperceptibility. However, uniform perturbations do not result in realistic AEs in domains such as malware, finance, and social networks. For these types of applications, features typically have some semantically meaningful dependencies. The key idea of our proposed approach is to enable non-uniform perturbations that can adequately represent these feature dependencies during adversarial training. We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. Using experimental datasets for malware classification, credit risk prediction, and spam detection, we show that our approach is more robust to real-world attacks. Finally, we present robustness certification utilizing non-uniform perturbation bounds, and show that non-uniform bounds achieve better certification.
Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input space, allow the attacker to greatly scale up the generation of such examples. Although UAPs have been explored in application domains beyond computer vision, little is known about their properties and implications in the specific context of realizable attacks, such as malware, where attackers must satisfy challenging problem-space constraints. In this paper we explore the challenges and strengths of UAPs in the context of malware classification. We generate sequences of problem-space transformations that induce UAPs in the corresponding feature-space embedding and evaluate their effectiveness across different malware domains. Additionally, we propose adversarial training-based mitigations using knowledge derived from the problem-space transformations, and compare against alternative feature-space defenses. Our experiments limit the effectiveness of a white box Android evasion attack to ~20% at the cost of ~3% TPR at 1% FPR. We additionally show how our method can be adapted to more restrictive domains such as Windows malware. We observe that while adversarial training in the feature space must deal with large and often unconstrained regions, UAPs in the problem space identify specific vulnerabilities that allow us to harden a classifier more effectively, shifting the challenges and associated cost of identifying new universal adversarial transformations back to the attacker.