Biblio

This paper presents a control strategy for Cyber-Physical System defense developed in the framework of the European Project ATENA, that concerns Critical Infrastructure (CI) protection. The aim of the controller is to find the optimal security configuration, in terms of countermeasures to implement, in order to address the system vulnerabilities. The attack/defense problem is modeled as a multi-agent general sum game, where the aim of the defender is to prevent the most damage possible by finding an optimal trade-off between prevention actions and their costs. The problem is solved utilizing Reinforcement Learning and simulation results provide a proof of the proposed concept, showing how the defender of the protected CI is able to minimize the damage caused by his her opponents by finding the Nash equilibrium of the game in the zero-sum variant, and, in a more general scenario, by driving the attacker in the position where the damage she/he can cause to the infrastructure is lower than the cost it has to sustain to enforce her/his attack strategy.

Information security has become a growing concern. Computer covert channel which is regarded as an important area of information security research gets more attention. In order to detect these covert channels, a variety of detection algorithms are proposed in the course of the research. The algorithms of machine learning type show better results in these detection algorithms. However, the common machine learning algorithms have many problems in the testing process and have great limitations. Based on the deep learning algorithm, this paper proposes a new idea of network covert channel detection and forms a new detection model. On the one hand, this algorithmic model can detect more complex covert channels and, on the other hand, greatly improve the accuracy of detection due to the use of a new deep learning model. By optimizing this test model, we can get better results on the evaluation index.

A covert channel is a communication channel that is subjugated for illegal flow of information in a way that violates system security policies. It is a dangerous, invisible, undetectable, and developed security attack. Recently, Packet length covert channel has motivated many researchers as it is a one of the most undetectable network covert channels. Packet length covert channel generates a covert traffic that is very similar to normal terrific which complicates the detection of such type of covert channels. This motivates us to introduce a machine learning based detection scheme. Recently, a machine learning approach has proved its capability in many different fields especially in security field as it usually brings up a reliable and realistic results. Based in our developed content and frequency-based features, the developed detection scheme has been fully trained and tested. Our detection scheme has gained an excellent degree of detection accuracy which reaches 98% (zero false negative rate and 0.02 false positive rate).

Algorithms are used to develop, analyzing, and applying in the computer field and used for developing new application. It is used for finding solutions to any problems in different condition. It transforms the problems into algorithmic ones on which standard algorithms are applied. Day by day Scholarly Digital documents are increasing. AlgorithmSeer is a search engine used for searching algorithms. The main aim of it provides a large algorithm database. It is used to automatically encountering and take these algorithms in this big collection of documents that enable algorithm indexing, searching, discovery, and analysis. An original set to identify and pull out algorithm representations in a big collection of scholarly documents is proposed, of scale able techniques used by AlgorithmSeer. Along with this, particularly important and relevant textual content can be accessed the platform and highlight portions by anyone with different levels of knowledge. In support of lectures and self-learning, the highlighted documents can be shared with others. But different levels of learners cannot use the highlighted part of text at same understanding level. The problem of guessing new highlights of partially highlighted documents can be solved by us.

Advancements in semiconductor domain gave way to realize numerous applications in Video Surveillance using Computer vision and Deep learning, Video Surveillances in Industrial automation, Security, ADAS, Live traffic analysis etc. through image understanding improves efficiency. Image understanding requires input data with high precision which is dependent on Image resolution and location of camera. The data of interest can be thermal image or live feed coming for various sensors. Composite(CVBS) is a popular video interface capable of streaming upto HD(1920x1080) quality. Unlike high speed serial interfaces like HDMI/MIPI CSI, Analog composite video interface is a single wire standard supporting longer distances. Image understanding requires edge detection and classification for further processing. Sobel filter is one the most used edge detection filter which can be embedded into live stream. This paper proposes Zynq FPGA based system design for video surveillance with Sobel edge detection, where the input Composite video decoded (Analog CVBS input to YCbCr digital output), processed in HW and streamed to HDMI display simultaneously storing in SD memory for later processing. The HW design is scalable for resolutions from VGA to Full HD for 60fps and 4K for 24fps. The system is built on Xilinx ZC702 platform and TVP5146 to showcase the functional path.

With the rapid development of information technology, video surveillance system has become a key part in the security and protection system of modern cities. Especially in prisons, surveillance cameras could be found almost everywhere. However, with the continuous expansion of the surveillance network, surveillance cameras not only bring convenience, but also produce a massive amount of monitoring data, which poses huge challenges to storage, analytics and retrieval. The smart monitoring system equipped with intelligent video analytics technology can monitor as well as pre-alarm abnormal events or behaviours, which is a hot research direction in the field of surveillance. This paper combines deep learning methods, using the state-of-the-art framework for instance segmentation, called Mask R-CNN, to train the fine-tuning network on our datasets, which can efficiently detect objects in a video image while simultaneously generating a high-quality segmentation mask for each instance. The experiment show that our network is simple to train and easy to generalize to other datasets, and the mask average precision is nearly up to 98.5% on our own datasets.

Anomaly detection on security logs is receiving more and more attention. Authentication events are an important component of security logs, and being able to produce trustful and accurate predictions minimizes the effort of cyber-experts to stop false attacks. Observed events are classified into Normal, for legitimate user behavior, and Malicious, for malevolent actions. These classes are consistently excessively imbalanced which makes the classification problem harder; in the commonly used Los Alamos dataset, the malicious class comprises only 0.00033% of the total. This work proposes a novel method to extract advanced composite features, and a supervised learning technique for classifying authentication logs trustfully; the models are Random Forest, LogitBoost, Logistic Regression, and ultimately Majority Voting which leverages the predictions of the previous models and gives the final prediction for each authentication event. We measure the performance of our experiments by using the False Negative Rate and False Positive Rate. In overall we achieve 0 False Negative Rate (i.e. no attack was missed), and on average a False Positive Rate of 0.0019.

Software insecurity is being identified as one of the leading causes of security breaches. In this paper, we revisited one of the strategies in solving software insecurity, which is the use of software quality metrics. We utilized a multilayer deep feedforward network in examining whether there is a combination of metrics that can predict the appearance of security-related bugs. We also applied the traditional machine learning algorithms such as decision tree, random forest, naïve bayes, and support vector machines and compared the results with that of the Deep Learning technique. The results have successfully demonstrated that it was possible to develop an effective predictive model to forecast software insecurity based on the software metrics and using Deep Learning. All the models generated have shown an accuracy of more than sixty percent with Deep Learning leading the list. This finding proved that utilizing Deep Learning methods and a combination of software metrics can be tapped to create a better forecasting model thereby aiding software developers in predicting security bugs.

Critical Infrastructures (CIs) use Supervisory Control And Data Acquisition (SCADA) systems for remote control and monitoring. Sophisticated security measures are needed to address malicious intrusions, which are steadily increasing in number and variety due to the massive spread of connectivity and standardisation of open SCADA protocols. Traditional Intrusion Detection Systems (IDSs) cannot detect attacks that are not already present in their databases. Therefore, in this paper, we assess Machine Learning (ML) for intrusion detection in SCADA systems using a real data set collected from a gas pipeline system and provided by the Mississippi State University (MSU). The contribution of this paper is two-fold: 1) The evaluation of four techniques for missing data estimation and two techniques for data normalization, 2) The performances of Support Vector Machine (SVM), and Random Forest (RF) are assessed in terms of accuracy, precision, recall and F1score for intrusion detection. Two cases are differentiated: binary and categorical classifications. Our experiments reveal that RF detect intrusions effectively, with an F1score of respectively \textbackslashtextgreater 99%.

Traditional anti-virus technologies have failed to keep pace with proliferation of malware due to slow process of their signatures and heuristics updates. Similarly, there are limitations of time and resources in order to perform manual analysis on each malware. There is a need to learn from this vast quantity of data, containing cyber attack pattern, in an automated manner to proactively adapt to ever-evolving threats. Machine learning offers unique advantages to learn from past cyber attacks to handle future cyber threats. The purpose of this research is to propose a framework for multi-classification of malware into well-known categories by applying different machine learning models over corpus of malware analysis reports. These reports are generated through an open source malware sandbox in an automated manner. We applied extensive pre-modeling techniques for data cleaning, features exploration and features engineering to prepare training and test datasets. Best possible hyper-parameters are selected to build machine learning models. These prepared datasets are then used to train the machine learning classifiers and to compare their prediction accuracy. Finally, these results are validated through a comprehensive 10-fold cross-validation methodology. The best results are achieved through Gaussian Naive Bayes classifier with random accuracy of 96% and 10-Fold Cross Validation accuracy of 91.2%. The said framework can be deployed in an operational environment to learn from malware attacks for proactively adapting matching counter measures.

Recently researchers have proposed using deep learning-based systems for malware detection. Unfortunately, all deep learning classification systems are vulnerable to adversarial learning-based attacks, or adversarial attacks, where miscreants can avoid detection by the classification algorithm with very few perturbations of the input data. Previous work has studied adversarial attacks against static analysis-based malware classifiers which only classify the content of the unknown file without execution. However, since the majority of malware is either packed or encrypted, malware classification based on static analysis often fails to detect these types of files. To overcome this limitation, anti-malware companies typically perform dynamic analysis by emulating each file in the anti-malware engine or performing in-depth scanning in a virtual machine. These strategies allow the analysis of the malware after unpacking or decryption. In this work, we study different strategies of crafting adversarial samples for dynamic analysis. These strategies operate on sparse, binary inputs in contrast to continuous inputs such as pixels in images. We then study the effects of two, previously proposed defensive mechanisms against crafted adversarial samples including the distillation and ensemble defenses. We also propose and evaluate the weight decay defense. Experiments show that with these three defenses, the number of successfully crafted adversarial samples is reduced compared to an unprotected baseline system. In particular, the ensemble defense is the most resilient to adversarial attacks. Importantly, none of the defenses significantly reduce the classification accuracy for detecting malware. Finally, we show that while adding additional hidden layers to neural models does not significantly improve the malware classification accuracy, it does significantly increase the classifier's robustness to adversarial attacks.

Malware detection is an indispensable factor in security of internet oriented machines. The combinations of different features are used for dynamic malware analysis. The different combinations are generated from APIs, Summary Information, DLLs and Registry Keys Changed. Cuckoo sandbox is used for dynamic malware analysis, which is customizable, and provide good accuracy. More than 2300 features are extracted from dynamic analysis of malware and 92 features are extracted statically from binary malware using PEFILE. Static features are extracted from 39000 malicious binaries and 10000 benign files. Dynamically 800 benign files and 2200 malware files are analyzed in Cuckoo Sandbox and 2300 features are extracted. The accuracy of dynamic malware analysis is 94.64% while static analysis accuracy is 99.36%. The dynamic malware analysis is not effective due to tricky and intelligent behaviours of malwares. The dynamic analysis has some limitations due to controlled network behavior and it cannot be analyzed completely due to limited access of network.

Early detection of new kinds of malware always plays an important role in defending the network systems. Especially, if intelligent protection systems could themselves detect an existence of new malware types in their system, even with a very small number of malware samples, it must be a huge benefit for the organization as well as the social since it help preventing the spreading of that kind of malware. To deal with learning from few samples, term ``one-shot learning'' or ``fewshot learning'' was introduced, and mostly used in computer vision to recognize images, handwriting, etc. An approach introduced in this paper takes advantage of One-shot learning algorithms in solving the malware classification problem by using Memory Augmented Neural Network in combination with malware's API calls sequence, which is a very valuable source of information for identifying malware behavior. In addition, it also use some advantages of the development in Natural Language Processing field such as word2vec, etc. to convert those API sequences to numeric vectors before feeding to the one-shot learning network. The results confirm very good accuracies compared to the other traditional methods.

The increasing amount of malware variants seen in the wild is causing problems for Antivirus Software vendors, unable to keep up by creating signatures for each. The methods used to develop a signature, static and dynamic analysis, have various limitations. Machine learning has been used by Antivirus vendors to detect malware based on the information gathered from the analysis process. However, adversarial examples can cause machine learning algorithms to miss-classify new data. In this paper we describe a method for malware analysis by converting malware binaries to images and then preparing those images for training within a Generative Adversarial Network. These unsupervised deep neural networks are not susceptible to adversarial examples. The conversion to images from malware binaries should be faster than using dynamic analysis and it would still be possible to link malware families together. Using the Generative Adversarial Network, malware detection could be much more effective and reliable.

With the increase in the popularity of computerized online applications, the analysis, and detection of a growing number of newly discovered stealthy malware poses a significant challenge to the security community. Signature-based and behavior-based detection techniques are becoming inefficient in detecting new unknown malware. Machine learning solutions are employed to counter such intelligent malware and allow performing more comprehensive malware detection. This capability leads to an automatic analysis of malware behavior. The proposed oblique random forest ensemble learning technique is efficient for malware classification. The effectiveness of the proposed method is demonstrated with three malware classification datasets from various sources. The results are compared with other variants of decision tree learning models. The proposed system performs better than the existing system in terms of classification accuracy and false positive rate.

Lately, we are facing the Malware crisis due to various types of malware or malicious programs or scripts available in the huge virtual world - the Internet. But, what is malware? Malware can be a malicious software or a program or a script which can be harmful to the user's computer. These malicious programs can perform a variety of functions, including stealing, encrypting or deleting sensitive data, altering or hijacking core computing functions and monitoring users' computer activity without their permission. There are various entry points for these programs and scripts in the user environment, but only one way to remove them is to find them and kick them out of the system which isn't an easy job as these small piece of script or code can be anywhere in the user system. This paper involves the understanding of different types of malware and how we will use Machine Learning to detect these malwares.

In this paper, we propose a deep learning framework for malware classification. There has been a huge increase in the volume of malware in recent years which poses a serious security threat to financial institutions, businesses and individuals. In order to combat the proliferation of malware, new strategies are essential to quickly identify and classify malware samples so that their behavior can be analyzed. Machine learning approaches are becoming popular for classifying malware, however, most of the existing machine learning methods for malware classification use shallow learning algorithms (e.g. SVM). Recently, Convolutional Neural Networks (CNN), a deep learning approach, have shown superior performance compared to traditional learning algorithms, especially in tasks such as image classification. Motivated by this success, we propose a CNN-based architecture to classify malware samples. We convert malware binaries to grayscale images and subsequently train a CNN for classification. Experiments on two challenging malware classification datasets, Malimg and Microsoft malware, demonstrate that our method achieves better than the state-of-the-art performance. The proposed method achieves 98.52% and 99.97% accuracy on the Malimg and Microsoft datasets respectively.

In recent years, deep convolution neural networks (DCNNs) have won many contests in machine learning, object detection, and pattern recognition. Furthermore, deep learning techniques achieved exceptional performance in image classification, reaching accuracy levels beyond human capability. Malware variants from similar categories often contain similarities due to code reuse. Converting malware samples into images can cause these patterns to manifest as image features, which can be exploited for DCNN classification. Techniques for converting malware binaries into images for visualization and classification have been reported in the literature, and while these methods do reach a high level of classification accuracy on training datasets, they tend to be vulnerable to overfitting and perform poorly on previously unseen samples. In this paper, we explore and document a variety of techniques for representing malware binaries as images with the goal of discovering a format best suited for deep learning. We implement a database for malware binaries from several families, stored in hexadecimal format. These malware samples are converted into images using various approaches and are used to train a neural network to recognize visual patterns in the input and classify malware based on the feature vectors. Each image type is assessed using a variety of learning models, such as transfer learning with existing DCNN architectures and feature extraction for support vector machine classifier training. Each technique is evaluated in terms of classification accuracy, result consistency, and time per trial. Our preliminary results indicate that improved image representation has the potential to enable more effective classification of new malware.

Better understanding of mobile applications' behaviors would lead to better malware detection/classification and better app recommendation for users. In this work, we design a framework AppDNA to automatically generate a compact representation for each app to comprehensively profile its behaviors. The behavior difference between two apps can be measured by the distance between their representations. As a result, the versatile representation can be generated once for each app, and then be used for a wide variety of objectives, including malware detection, app categorizing, plagiarism detection, etc. Based on a systematic and deep understanding of an app's behavior, we propose to perform a function-call-graph-based app profiling. We carefully design a graph-encoding method to convert a typically extremely large call-graph to a 64-dimension fix-size vector to achieve robust app profiling. Our extensive evaluations based on 86,332 benign and malicious apps demonstrate that our system performs app profiling (thus malware detection, classification, and app recommendation) to a high accuracy with extremely low computation cost: it classifies 4024 (benign/malware) apps using around 5.06 second with accuracy about 93.07%; it classifies 570 malware's family (total 21 families) using around 0.83 second with accuracy 82.3%; it classifies 9,730 apps' functionality with accuracy 33.3% for a total of 7 categories and accuracy of 88.1 % for 2 categories.

In this paper we present a new approach, named DLGraph, for malware detection using deep learning and graph embedding. DLGraph employs two stacked denoising autoencoders (SDAs) for representation learning, taking into consideration computer programs' function-call graphs and Windows application programming interface (API) calls. Given a program, we first use a graph embedding technique that maps the program's function-call graph to a vector in a low-dimensional feature space. One SDA in our deep learning model is used to learn a latent representation of the embedded vector of the function-call graph. The other SDA in our model is used to learn a latent representation of the given program's Windows API calls. The two learned latent representations are then merged to form a combined feature vector. Finally, we use softmax regression to classify the combined feature vector for predicting whether the given program is malware or not. Experimental results based on different datasets demonstrate the effectiveness of the proposed approach and its superiority over a related method.

Security has always been a major issue in cloud. Data sources are the most valuable and vulnerable information which is aimed by attackers to steal. If data is lost, then the privacy and security of every cloud user are compromised. Even though a cloud network is secured externally, the threat of an internal attacker exists. Internal attackers compromise a vulnerable user node and get access to a system. They are connected to the cloud network internally and launch attacks pretending to be trusted users. Machine learning approaches are widely used for cloud security issues. The existing machine learning based security approaches classify a node as a misbehaving node based on short-term behavioral data. These systems do not differentiate whether a misbehaving node is a malicious node or a broken node. To address this problem, this paper proposes an Improvised Long Short-Term Memory (ILSTM) model which learns the behavior of a user and automatically trains itself and stores the behavioral data. The model can easily classify the user behavior as normal or abnormal. The proposed ILSTM not only identifies an anomaly node but also finds whether a misbehaving node is a broken node or a new user node or a compromised node using the calculated trust factor. The proposed model not only detects the attack accurately but also reduces the false alarm in the cloud network.

Modern industrial control systems (ICS) act as victims of cyber attacks more often in last years. These attacks are hard to detect and their consequences can be catastrophic. Cyber attacks can cause anomalies in the work of the ICS and its technological equipment. The presence of mutual interference and noises in this equipment significantly complicates anomaly detection. Moreover, the traditional means of protection, which used in corporate solutions, require updating with each change in the structure of the industrial process. An approach based on the machine learning for anomaly detection was used to overcome these problems. It complements traditional methods and allows one to detect signal correlations and use them for anomaly detection. Additional Tennessee Eastman Process Simulation Data for Anomaly Detection Evaluation dataset was analyzed as example of industrial process. In the course of the research, correlations between the signals of the sensors were detected and preliminary data processing was carried out. Algorithms from the most common techniques of machine learning (decision trees, linear algorithms, support vector machines) and deep learning models (neural networks) were investigated for industrial process anomaly detection task. It's shown that linear algorithms are least demanding on computational resources, but they don't achieve an acceptable result and allow a significant number of errors. Decision tree-based algorithms provided an acceptable accuracy, but the amount of RAM, required for their operations, relates polynomially with the training sample volume. The deep neural networks provided the greatest accuracy, but they require considerable computing power for internal calculations.

With the exponential hike in cyber threats, organizations are now striving for better data mining techniques in order to analyze security logs received from their IT infrastructures to ensure effective and automated cyber threat detection. Machine Learning (ML) based analytics for security machine data is the next emerging trend in cyber security, aimed at mining security data to uncover advanced targeted cyber threats actors and minimizing the operational overheads of maintaining static correlation rules. However, selection of optimal machine learning algorithm for security log analytics still remains an impeding factor against the success of data science in cyber security due to the risk of large number of false-positive detections, especially in the case of large-scale or global Security Operations Center (SOC) environments. This fact brings a dire need for an efficient machine learning based cyber threat detection model, capable of minimizing the false detection rates. In this paper, we are proposing optimal machine learning algorithms with their implementation framework based on analytical and empirical evaluations of gathered results, while using various prediction, classification and forecasting algorithms.

The Machine Type Communication Devices (MTCDs) are usually based on Internet Protocol (IP), which can cause billions of connected objects to be part of the Internet. The enormous amount of data coming from these devices are quite heterogeneous in nature, which can lead to security issues, such as injection attacks, ballot stuffing, and bad mouthing. Consequently, this work considers machine learning trust evaluation as an effective and accurate option for solving the issues associate with security threats. In this paper, a comparative analysis is carried out with five different machine learning approaches: Naive Bayes (NB), Decision Tree (DT), Linear and Radial Support Vector Machine (SVM), KNearest Neighbor (KNN), and Random Forest (RF). As a critical element of the research, the recommendations consider different Machine-to-Machine (M2M) communication nodes with regard to their ability to identify malicious and honest information. To validate the performances of these models, two trust computation measures were used: Receiver Operating Characteristics (ROCs), Precision and Recall. The malicious data was formulated in Matlab. A scenario was created where 50% of the information were modified to be malicious. The malicious nodes were varied in the ranges of 10%, 20%, 30%, 40%, and the results were carefully analyzed.

Physical Unclonable Functions (PUFs) have been designed for many security applications such as identification, authentication of devices and key generation, especially for lightweight electronics. Traditional approaches to enhancing security, such as hash functions, may be expensive and resource dependent. However, modelling attacks using machine learning (ML) show the vulnerability of most PUFs. In this paper, a combination of a 32-bit current mirror and 16-bit arbiter PUFs in 65nm CMOS technology is proposed to improve resilience against modelling attacks. Both PUFs are vulnerable to machine learning attacks and we reduce the output prediction rate from 99.2% and 98.8% individually, to 60%.