Feature Analysis of Encrypted Malicious Traffic

In recent years there has been a dramatic increase in the number of malware attacks that use encrypted HTTP traffic for self-propagation or communication. Antivirus software and firewalls typically will not have access to encryption keys, and therefore direct detection of malicious encrypted data is unlikely to succeed. However, previous work has shown that traffic analysis can provide indications of malicious intent, even in cases where the underlying data remains encrypted. In this paper, we apply three machine learning techniques to the problem of distinguishing malicious encrypted HTTP traffic from benign encrypted traffic and obtain results comparable to previous work. We then consider the problem of feature analysis in some detail. Previous work has often relied on human expertise to determine the most useful and informative features in this problem domain. We demonstrate that such feature-related information can be obtained directly from machine learning models themselves. We argue that such a machine learning based approach to feature analysis is preferable, as it is more reliable, and we can, for example, uncover relatively unintuitive interactions between features.

Social Media Bot Detection using Dropout-GAN

Bot activity on social media platforms is a pervasive problem, undermining the credibility of online discourse and potentially leading to cybercrime. We propose an approach to bot detection using Generative Adversarial Networks (GAN). We discuss how we overcome the issue of mode collapse by utilizing multiple discriminators to train against one generator, while decoupling the discriminator to perform social media bot detection and utilizing the generator for data augmentation. In terms of classification accuracy, our approach outperforms the state-of-the-art techniques in this field. We also show how the generator in the GAN can be used to evade such a classification technique.

On the Steganographic Capacity of Selected Learning Models

Machine learning and deep learning models are potential vectors for various attack scenarios. For example, previous research has shown that malware can be hidden in deep learning models. Hiding information in a learning model can be viewed as a form of steganography. In this research, we consider the general question of the steganographic capacity of learning models. Specifically, for a wide range of models, we determine the number of low-order bits of the trained parameters that can be overwritten, without adversely affecting model performance. For each model considered, we graph the accuracy as a function of the number of low-order bits that have been overwritten, and for selected models, we also analyze the steganographic capacity of individual layers. The models that we test include the classic machine learning techniques of Linear Regression (LR) and Support Vector Machine (SVM); the popular general deep learning models of Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN); the highly-successful Recurrent Neural Network (RNN) architecture of Long Short-Term Memory (LSTM); the pre-trained transfer learning-based models VGG16, DenseNet121, InceptionV3, and Xception; and, finally, an Auxiliary Classifier Generative Adversarial Network (ACGAN). In all cases, we find that a majority of the bits of each trained parameter can be overwritten before the accuracy degrades. Of the models tested, the steganographic capacity ranges from 7.04 KB for our LR experiments, to 44.74 MB for InceptionV3. We discuss the implications of our results and consider possible avenues for further research.

A Comparison of Adversarial Learning Techniques for Malware Detection

Machine learning has proven to be a useful tool for automated malware detection, but machine learning models have also been shown to be vulnerable to adversarial attacks. This article addresses the problem of generating adversarial malware samples, specifically malicious Windows Portable Executable files. We summarize and compare work that has focused on adversarial machine learning for malware detection. We use gradient-based, evolutionary algorithm-based, and reinforcement-based methods to generate adversarial samples, and then test the generated samples against selected antivirus products. We compare the selected methods in terms of accuracy and practical applicability. The results show that applying optimized modifications to previously detected malware can lead to incorrect classification of the file as benign. It is also known that generated malware samples can be successfully used against detection models other than those used to generate them and that using combinations of generators can create new samples that evade detection. Experiments show that the Gym-malware generator, which uses a reinforcement learning approach, has the greatest practical potential. This generator achieved an average sample generation time of 5.73 seconds and the highest average evasion rate of 44.11%. Using the Gym-malware generator in combination with itself improved the evasion rate to 58.35%.

Hidden Markov Models with Random Restarts vs Boosting for Malware Detection

Effective and efficient malware detection is at the forefront of research into building secure digital systems. As with many other fields, malware detection research has seen a dramatic increase in the application of machine learning algorithms. One machine learning technique that has been used widely in the field of pattern matching in general-and malware detection in particular-is hidden Markov models (HMMs). HMM training is based on a hill climb, and hence we can often improve a model by training multiple times with different initial values. In this research, we compare boosted HMMs (using AdaBoost) to HMMs trained with multiple random restarts, in the context of malware detection. These techniques are applied to a variety of challenging malware datasets. We find that random restarts perform surprisingly well in comparison to boosting. Only in the most difficult "cold start" cases (where training data is severely limited) does boosting appear to offer sufficient improvement to justify its higher computational cost in the scoring phase.

A Natural Language Processing Approach to Malware Classification

Many different machine learning and deep learning techniques have been successfully employed for malware detection and classification. Examples of popular learning techniques in the malware domain include Hidden Markov Models (HMM), Random Forests (RF), Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Recurrent Neural Networks (RNN) such as Long Short-Term Memory (LSTM) networks. In this research, we consider a hybrid architecture, where HMMs are trained on opcode sequences, and the resulting hidden states of these trained HMMs are used as feature vectors in various classifiers. In this context, extracting the HMM hidden state sequences can be viewed as a form of feature engineering that is somewhat analogous to techniques that are commonly employed in Natural Language Processing (NLP). We find that this NLP-based approach outperforms other popular techniques on a challenging malware dataset, with an HMM-Random Forrest model yielding the best results.

Keystroke Dynamics for User Identification

In previous research, keystroke dynamics has shown promise for user authentication, based on both fixed-text and free-text data. In this research, we consider the more challenging multiclass user identification problem, based on free-text data. We experiment with a complex image-like feature that has previously been used to achieve state-of-the-art authentication results over free-text data. Using this image-like feature and multiclass Convolutional Neural Networks, we are able to obtain a classification (i.e., identification) accuracy of 0.78 over a set of 148 users. However, we find that a Random Forest classifier trained on a slightly modified version of this same feature yields an accuracy of 0.93.

Classifying World War II Era Ciphers with Machine Learning

We determine the accuracy with which machine learning and deep learning techniques can classify selected World War II era ciphers when only ciphertext is available. The specific ciphers considered are Enigma, M-209, Sigaba, Purple, and Typex. We experiment with three classic machine learning models, namely, Support Vector Machines (SVM), $k$-Nearest Neighbors ($k$-NN), and Random Forest (RF). We also experiment with four deep learning neural network-based models: Multi-Layer Perceptrons (MLP), Long Short-Term Memory (LSTM), Extreme Learning Machines (ELM), and Convolutional Neural Networks (CNN). Each model is trained on features consisting of histograms, digrams, and raw ciphertext letter sequences. Furthermore, the classification problem is considered under four distinct scenarios: Fixed plaintext with fixed keys, random plaintext with fixed keys, fixed plaintext with random keys, and random plaintext with random keys. Under the most realistic scenario, given 1000 characters per ciphertext, we are able to distinguish the ciphers with greater than 97% accuracy. In addition, we consider the accuracy of a subset of the learning techniques as a function of the length of the ciphertext messages. Somewhat surprisingly, our classic machine learning models perform at least as well as our deep learning models. We also find that ciphers that are more similar in design are somewhat more challenging to distinguish, but not as difficult as might be expected.

Steganographic Capacity of Deep Learning Models

As machine learning and deep learning models become ubiquitous, it is inevitable that there will be attempts to exploit such models in various attack scenarios. For example, in a steganographic-based attack, information could be hidden in a learning model, which might then be used to distribute malware, or for other malicious purposes. In this research, we consider the steganographic capacity of several learning models. Specifically, we train a Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Transformer model on a challenging malware classification problem. For each of the resulting models, we determine the number of low-order bits of the trained parameters that can be altered without significantly affecting the performance of the model. We find that the steganographic capacity of the learning models tested is surprisingly high, and that in each case, there is a clear threshold after which model performance rapidly degrades.

Creating Valid Adversarial Examples of Malware

Machine learning is becoming increasingly popular as a go-to approach for many tasks due to its world-class results. As a result, antivirus developers are incorporating machine learning models into their products. While these models improve malware detection capabilities, they also carry the disadvantage of being susceptible to adversarial attacks. Although this vulnerability has been demonstrated for many models in white-box settings, a black-box attack is more applicable in practice for the domain of malware detection. We present a generator of adversarial malware examples using reinforcement learning algorithms. The reinforcement learning agents utilize a set of functionality-preserving modifications, thus creating valid adversarial examples. Using the proximal policy optimization (PPO) algorithm, we achieved an evasion rate of 53.84% against the gradient-boosted decision tree (GBDT) model. The PPO agent previously trained against the GBDT classifier scored an evasion rate of 11.41% against the neural network-based classifier MalConv and an average evasion rate of 2.31% against top antivirus programs. Furthermore, we discovered that random application of our functionality-preserving portable executable modifications successfully evades leading antivirus engines, with an average evasion rate of 11.65%. These findings indicate that machine learning-based models used in malware detection systems are vulnerable to adversarial attacks and that better safeguards need to be taken to protect these systems.