Biblio

Vulnerability detection is an import issue in information system security. In this work, we propose the deep learning method for vulnerability detection. We present three deep learning models, namely, convolution neural network (CNN), long short term memory (LSTM) and convolution neural network — long short term memory (CNN-LSTM). In order to test the performance of our approach, we collected 9872 sequences of function calls as features to represent the patterns of binary programs during their execution. We apply our deep learning models to predict the vulnerabilities of these binary programs based on the collected data. The experimental results show that the prediction accuracy of our proposed method reaches 83.6%, which is superior to that of traditional method like multi-layer perceptron (MLP).

Block recursive least square (BRLS) algorithm for dictionary learning in compressed sensing system is developed for surveillance video processing. The new method uses image blocks directly and iteratively to train dictionaries via BRLS algorithm, which is different from classical methods that require to transform blocks to columns first and then giving all training blocks at one time. Since the background in surveillance video is almost fixed, the residual of foreground can be represented sparsely and reconstructed with background subtraction directly. The new method and framework are applied in real image and surveillance video processing. Simulation results show that the new method achieves better representation performance than classical ones in both image and surveillance video.

In video surveillance, face recognition (FR) systems seek to detect individuals of interest appearing over a distributed network of cameras. Still-to-video FR systems match faces captured in videos under challenging conditions against facial models, often designed using one reference still per individual. Although CNNs can achieve among the highest levels of accuracy in many real-world FR applications, state-of-the-art CNNs that are suitable for still-to-video FR, like trunk-branch ensemble (TBE) CNNs, represent complex solutions for real-time applications. In this paper, an efficient CNN architecture is proposed for accurate still-to-video FR from a single reference still. The CCM-CNN is based on new cross-correlation matching (CCM) and triplet-loss optimization methods that provide discriminant face representations. The matching pipeline exploits a matrix Hadamard product followed by a fully connected layer inspired by adaptive weighted cross-correlation. A triplet-based training approach is proposed to optimize the CCM-CNN parameters such that the inter-class variations are increased, while enhancing robustness to intra-class variations. To further improve robustness, the network is fine-tuned using synthetically-generated faces based on still and videos of non-target individuals. Experiments on videos from the COX Face and Chokepoint datasets indicate that the CCM-CNN can achieve a high level of accuracy that is comparable to TBE-CNN and HaarNet, but with a significantly lower time and memory complexity. It may therefore represent the better trade-off between accuracy and complexity for real-time video surveillance applications.

Surveillance video systems are gaining increasing attention in the field of computer vision due to its demands of users for the seek of security. It is promising to observe the human movement and predict such kind of sense of movements. The need arises to develop a surveillance system that capable to overcome the shortcoming of depending on the human resource to stay monitoring, observing the normal and suspect event all the time without any absent mind and to facilitate the control of huge surveillance system network. In this paper, an intelligent human activity system recognition is developed. Series of digital image processing techniques were used in each stage of the proposed system, such as background subtraction, binarization, and morphological operation. A robust neural network was built based on the human activities features database, which was extracted from the frame sequences. Multi-layer feed forward perceptron network used to classify the activities model in the dataset. The classification results show a high performance in all of the stages of training, testing and validation. Finally, these results lead to achieving a promising performance in the activity recognition rate.

Wearable Internet-of-Things (WIoT) environments have demonstrated great potential in a broad range of applications in healthcare and well-being. Security is essential for WIoT environments. Lack of security in WIoTs not only harms user privacy, but may also harm the user's safety. Though devices in the WIoT can be attacked in many ways, in this paper we focus on adversaries who mount what we call sensor-hijacking attacks, which prevent the constituent medical devices from accurately collecting and reporting the user's health state (e.g., reporting old or wrong physiological measurements). In this paper we outline some of our experiences in implementing a data-driven security solution for detecting sensor-hijacking attack on a secure wearable internet-of-things (WIoT) base station called the Amulet. Given the limited capabilities (computation, memory, battery power) of the Amulet platform, implementing such a security solution is quite challenging and presents several trade-offs with respect to detection accuracy and resources requirements. We conclude the paper with a list of insights into what capabilities constrained WIoT platforms should provide developers so as to make the inclusion of data-driven security primitives in such systems.

Hierarchical Graph Neuron (HGN) is an extension of network-centric algorithm called Graph Neuron (GN), which is used to perform parallel distributed pattern recognition. In this research, HGN scheme is used to classify intrusion attacks in computer networks. Patterns of intrusion attacks are preprocessed in three steps: selecting attributes using information gain attribute evaluation, discretizing the selected attributes using entropy-based discretization supervised method, and selecting the training data using K-Means clustering algorithm. After the preprocessing stage, the HGN scheme is then deployed to classify intrusion attack using the KDD Cup 99 dataset. The results of the classification are measured in terms of accuracy rate, detection rate, false positive rate and true negative rate. The test result shows that the HGN scheme is promising and stable in classifying the intrusion attack patterns with accuracy rate reaches 96.27%, detection rate reaches 99.20%, true negative rate below 15.73%, and false positive rate as low as 0.80%.

Deep Learning has been proven more effective than conventional machine-learning algorithms in solving classification problem with high dimensionality and complex features, especially when trained with big data. In this paper, a deep learning binomial classifier for Network Intrusion Detection System is proposed and experimentally evaluated using the UNSW-NB15 dataset. Three different experiments were executed in order to determine the optimal activation function, then to select the most important features and finally to test the proposed model on unseen data. The evaluation results demonstrate that the proposed classifier outperforms other models in the literature with 98.99% accuracy and 0.56% false alarm rate on unseen data.

This paper presents a novel feature learning model for cyber security tasks. We propose to use Auto-encoders (AEs), as a generative model, to learn latent representation of different feature sets. We show how well the AE is capable of automatically learning a reasonable notion of semantic similarity among input features. Specifically, the AE accepts a feature vector, obtained from cyber security phenomena, and extracts a code vector that captures the semantic similarity between the feature vectors. This similarity is embedded in an abstract latent representation. Because the AE is trained in an unsupervised fashion, the main part of this success comes from appropriate original feature set that is used in this paper. It can also provide more discriminative features in contrast to other feature engineering approaches. Furthermore, the scheme can reduce the dimensionality of the features thereby signicantly minimising the memory requirements. We selected two different cyber security tasks: networkbased anomaly intrusion detection and Malware classication. We have analysed the proposed scheme with various classifiers using publicly available datasets for network anomaly intrusion detection and malware classifications. Several appropriate evaluation metrics show improvement compared to prior results.

In the paper, we demonstrate a neuromorphic cognitive computing approach for Network Intrusion Detection System (IDS) for cyber security using Deep Learning (DL). The algorithmic power of DL has been merged with fast and extremely power efficient neuromorphic processors for cyber security. In this implementation, the data has been numerical encoded to train with un-supervised deep learning techniques called Auto Encoder (AE) in the training phase. The generated weights of AE are used as initial weights for the supervised training phase using neural networks. The final weights are converted to discrete values using Discrete Vector Factorization (DVF) for generating crossbar weight, synaptic weights, and thresholds for neurons. Finally, the generated crossbar weights, synaptic weights, threshold, and leak values are mapped to crossbars and neurons. In the testing phase, the encoded test samples are converted to spiking form by using hybrid encoding technique. The model has been deployed and tested on the IBM Neurosynaptic Core Simulator (NSCS) and on actual IBM TrueNorth neurosynaptic chip. The experimental results show around 90.12% accuracy for network intrusion detection for cyber security on the physical neuromorphic chip. Furthermore, we have investigated the proposed system not only for detection of malicious packets but also for classifying specific types of attacks and achieved 81.31% recognition accuracy. The neuromorphic implementation provides incredible detection and classification accuracy for network intrusion detection with extremely low power.

Intrusion Detection Systems (IDS) have been in existence for many years now, but they fall short in efficiently detecting zero-day attacks. This paper presents an organic combination of Semantic Link Networks (SLN) and dynamic semantic graph generation for the on the fly discovery of zero-day attacks using the Spark Streaming platform for parallel detection. In addition, a minimum redundancy maximum relevance (MRMR) feature selection algorithm is deployed to determine the most discriminating features of the dataset. Compared to previous studies on zero-day attack identification, the described method yields better results due to the semantic learning and reasoning on top of the training data and due to the use of collaborative classification methods. We also verified the scalability of our method in a distributed environment.

Machine learning and data mining algorithms typically assume that the training and testing data are sampled from the same fixed probability distribution; however, this violation is often violated in practice. The field of domain adaptation addresses the situation where this assumption of a fixed probability between the two domains is violated; however, the difference between the two domains (training/source and testing/target) may not be known a priori. There has been a recent thrust in addressing the problem of learning in the presence of an adversary, which we formulate as a problem of domain adaption to build a more robust classifier. This is because the overall security of classifiers and their preprocessing stages have been called into question with the recent findings of adversaries in a learning setting. Adversarial training (and testing) data pose a serious threat to scenarios where an attacker has the opportunity to ``poison'' the training or ``evade'' on the testing data set(s) in order to achieve something that is not in the best interest of the classifier. Recent work has begun to show the impact of adversarial data on several classifiers; however, the impact of the adversary on aspects related to preprocessing of data (i.e., dimensionality reduction or feature selection) has widely been ignored in the revamp of adversarial learning research. Furthermore, variable selection, which is a vital component to any data analysis, has been shown to be particularly susceptible under an attacker that has knowledge of the task. In this work, we explore avenues for learning resilient classification models in the adversarial learning setting by considering the effects of adversarial data and how to mitigate its effects through optimization. Our model forms a single convex optimization problem that uses the labeled training data from the source domain and known- weaknesses of the model for an adversarial component. We benchmark the proposed approach on synthetic data and show the trade-off between classification accuracy and skew-insensitive statistics.

Different data mining techniques are employed in stylometry domain for performing authorship attribution tasks. Sometimes to improve the decision system the discretization of input data can be applied. In many cases such approach allows to obtain better classification results. On the other hand, there were situations in which discretization decreased overall performance of the system. Therefore, the question arose what would be the result if only some selected attributes were discretized. The paper presents the results of the research performed for forward sequential selection of attributes to be discretized. The influence of such approach on the performance of the decision system, based on Naive Bayes classifier in authorship attribution domain, is presented. Some basic discretization methods and different approaches to discretization of the test datasets are taken into consideration.

The notion of style is pivotal to literature. The choice of a certain writing style moulds and enhances the overall character of a book. Stylometry uses statistical methods to analyze literary style. This work aims to build a recommendation system based on the similarity in stylometric cues of various authors. The problem at hand is in close proximity to the author attribution problem. It follows a supervised approach with an initial corpus of books labelled with their respective authors as training set and generate recommendations based on the misclassified books. Results in book similarity are substantiated by domain experts.

Dynamic security assessment provides system operators with vital information for possible preventive or emergency control to prevent security problems. In some cases, power system topology change deteriorates intelligent system-based online stability assessment performance. In this paper, we propose a new online assessment scheme to improve classification performance reliability of dynamic transient stability assessment. In the new scheme, we use an intelligent system consisting an ensemble of neural networks based on extreme learning machine. A new feature selection algorithm combining filter type method RRelief-F and wrapper type method Sequential Floating Forward Selection is proposed. Boosting learning algorithm is used in intelligent system training process which leads to higher classification accuracy. Moreover, we propose a new classification rule using weighted outputs of predictors in the ensemble helps to achieve 100% transient stability prediction in our case study.

Dynamic security assessment provides system operators with vital information for possible preventive or emergency control to prevent security problems. In some cases, power system topology change deteriorates intelligent system-based online stability assessment performance. In this paper, we propose a new online assessment scheme to improve classification performance reliability of dynamic transient stability assessment. In the new scheme, we use an intelligent system consisting an ensemble of neural networks based on extreme learning machine. A new feature selection algorithm combining filter type method RRelief-F and wrapper type method Sequential Floating Forward Selection is proposed. Boosting learning algorithm is used in intelligent system training process which leads to higher classification accuracy. Moreover, we propose a new classification rule using weighted outputs of predictors in the ensemble helps to achieve 100% transient stability prediction in our case study.

User attribution process based on human inherent dynamics and preference is one area of research that is capable of elucidating and capturing human dynamics on the Internet. Prior works on user attribution concentrated on behavioral biometrics, 1-to-1 user identification process without consideration for individual preference and human inherent temporal tendencies, which is capable of providing a discriminatory baseline for online users, as well as providing a higher level classification framework for novel user attribution. To address these limitations, the study developed a temporal model, which comprises the human Polyphasia tendency based on Polychronic-Monochronic tendency scale measurement instrument and the extraction of unique human-centric features from server-side network traffic of 48 active users. Several machine-learning algorithms were applied to observe distinct pattern among the classes of the Polyphasia tendency, through which a logistic model tree was observed to provide higher classification accuracy for a 1-to-N user attribution process. The study further developed a high-level attribution model for higher-level user attribution process. The result from this study is relevant in online profiling process, forensic identification and profiling process, e-learning profiling process as well as in social network profiling process.

Conventional intrusion detection systems for smart grid communications rely heavily on static based attack detection techniques. In essence, signatures created from historical data are compared to incoming network traffic to identify abnormalities. In the case of attacks where no historical data exists, static based approaches become ineffective thus relinquishing system resilience and stability. Moving target defense (MTD) has shown to be effective in discouraging attackers by introducing system entropy to increase exploit costs. Increase in exploit cost leads to a decrease in profitability for an attacker. In this paper, a Moving Target Defense Intrusion Detection System (MTDIDS) is proposed for smart grid IPv6 based advanced metering infrastructure. The advantage of MTDIDS is the ability to detect anomalies across moving targets by means of planar keys thereupon increasing detection rate. Evaluation of MTDIDS was carried out in a smart grid advanced metering infrastructure simulated in MATLAB.

There has been a great deal of work on learning new robot skills, but very little consideration of how these newly acquired skills can be integrated into an overall intelligent system. A key aspect of such a system is compositionality: newly learned abilities have to be characterized in a form that will allow them to be flexibly combined with existing abilities, affording a (good!) combinatorial explosion in the robot's abilities. In this paper, we focus on learning models of the preconditions and effects of new parameterized skills, in a form that allows those actions to be combined with existing abilities by a generative planning and execution system.

With the rapid application of the network based communication in industries, the security related problems appear to be inevitable for automation networks. The integration of internet into the automation plant benefited companies and engineers a lot and on the other side paved ways to number of threats. An attack on such control critical infrastructure may endangers people's health and safety, damage industrial facilities and produce financial loss. One of the approach to secure the network in automation is the development of an efficient Network based Intrusion Detection System (NIDS). Despite several techniques available for intrusion detection, they still lag in identifying the possible attacks or novel attacks on network efficiently. In this paper, we evaluate the performance of detection mechanism by combining the deep learning techniques with the machine learning techniques for the development of Intrusion Detection System (IDS). The performance metrics such as precession, recall and F-Measure were measured.

Generative policies enable devices to generate their own policies that are validated, consistent and conflict free. This autonomy is required for security policy generation to deal with the large number of smart devices per person that will soon become reality. In this paper, we discuss the research issues that have to be addressed in order for devices involved in security enforcement to automatically generate their security policies - enabling policy-based autonomous security management. We discuss the challenges involved in the task of automatic security policy generation, and outline some approaches based om machine learning that may potentially provide a solution to the same.

In the paper, we demonstrate novel approach for network Intrusion Detection System (IDS) for cyber security using unsupervised Deep Learning (DL) techniques. Very often, the supervised learning and rules based approach like SNORT fetch problem to identify new type of attacks. In this implementation, the input samples are numerical encoded and applied un-supervised deep learning techniques called Auto Encoder (AE) and Restricted Boltzmann Machine (RBM) for feature extraction and dimensionality reduction. Then iterative k-means clustering is applied for clustering on lower dimension space with only 3 features. In addition, Unsupervised Extreme Learning Machine (UELM) is used for network intrusion detection in this implementation. We have experimented on KDD-99 dataset, the experimental results show around 91.86% and 92.12% detection accuracy using unsupervised deep learning technique AE and RBM with K-means respectively. The experimental results also demonstrate, the proposed approach shows around 4.4% and 2.95% improvement of detection accuracy using RBM with K-means against only K-mean clustering and Unsupervised Extreme Learning Machine (USELM) respectively.

Biometrics has become ubiquitous and spurred common use in many authentication mechanisms. Keystroke dynamics is a form of behavioral biometrics that can be used for user authentication while actively working at a terminal. The proposed mechanisms involve digraph, trigraph and n-graph analysis as separate solutions or suggest a fusion mechanism with certain limitations. However, deep learning can be used as a unifying machine learning technique that consolidates the power of all different features since it has shown tremendous results in image recognition and natural language processing. In this paper, we investigate the applicability of deep learning on three different datasets by using convolutional neural networks and Gaussian data augmentation technique. We achieve 10% higher accuracy and 7.3% lower equal error rate (EER) than existing methods. Also, our sensitivity analysis indicates that the convolution operation and the fully-connected layer are the most prominent factors that affect the accuracy and the convergence rate of a network trained with keystroke data.

The modular multilevel converter with series and parallel connectivity was shown to provide advantages in several industrial applications. Its reliability largely depends on the absence of failures in the power semiconductors. We propose and analyze a fault-diagnosis technique to identify shorted switches based on features generated through wavelet transform of the converter output and subsequent classification in support vector machines. The multi-class support vector machine is trained with multiple recordings of the output of each fault condition as well as the converter under normal operation. Simulation results reveal that the proposed method has high classification latency and high robustness. Except for the monitoring of the output, which is required for the converter control in any case, this method does not require additional module sensors.

Bitcoin is the most famous cryptocurrency currently operating with a total marketcap of almost 7 billion USD. This innovation stands strong on the feature of pseudo anonymity and strives on its innovative de-centralized architecture based on the Blockchain. The Blockchain is a distributed ledger that keeps a public record of all the transactions processed on the bitcoin protocol network in full transparency without revealing the identity of the sender and the receiver. Over the course of 2016, cryptocurrencies have shown some instances of abuse by criminals in their activities due to its interesting nature. Darknet marketplaces are increasing the volume of their businesses in illicit and illegal trades but also cryptocurrencies have been used in cases of extortion, ransom and as part of sophisticated malware modus operandi. We tackle these challenges by developing an analytical capability that allows us to map relationships on the blockchain and filter crime instances in order to investigate the abuse in law enforcement local environment. We propose a practical bitcoin analytical process and an analyzing system that stands alone and manages all data on the blockchain in real-time with tracing and visualizing techniques rendering transactions decipherable and useful for law enforcement investigation and training. Our system adopts combination of analyzing methods that provides statistics of address, graphical transaction relation, discovery of paths and clustering of already known addresses. We evaluated our system in the three criminal cases includes marketplace, ransomware and DDoS extortion. These are practical training in law enforcement, then we determined whether our system could help investigation process and training.

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions.