Biblio

As system of systems (SoS) models become increasingly complex and interconnected a new approach is needed to capture the effects of humans within the SoS. Many real-life events have shown the detrimental outcomes of failing to account for humans in the loop. This research introduces a novel and cross-disciplinary methodology for modeling humans interacting with technologies to perform tasks within an SoS specifically within a layered physical security system use case. Metrics and formulations developed for this new way of looking at SoS termed sociotechnical SoS allow for the quantification of the interplay of effectiveness and efficiency seen in detection theory to measure the ability of a physical security system to detect and respond to threats. This methodology has been applied to a notional representation of a small military Forward Operating Base (FOB) as a proof-of-concept.

The detection of cyber-attacks has become a crucial task for highly sophisticated systems like industrial control systems (ICS). These systems are an essential part of critical information infrastructure. Therefore, we can highlight their vital role in contemporary society. The effective and reliable ICS cyber defense is a significant challenge for the cyber security community. Thus, intrusion detection is one of the demanding tasks for the cyber security researchers. In this article, we examine classification problem. The proposed detection system is based on supervised anomaly detection techniques. Moreover, we utilized classifiers algorithms in order to increase intrusion detection capabilities. The fusion of the classifiers is the way how to achieve the predefined goal.

Industrial control systems (ICS) used in industrial plants are vulnerable to cyber-attacks that can cause fatal damage to the plants. Intrusion detection systems (IDSs) monitor ICS network traffic and detect suspicious activities. However, many IDSs overlook sophisticated cyber-attacks because it is hard to make a complete database of cyber-attacks and distinguish operational anomalies when compared to an established baseline. In this paper, a discriminant model between normal and anomalous packets was constructed with a support vector machine (SVM) based on an ICS communication profile, which represents only packet intervals and length, and an IDS with the applied model is proposed. Furthermore, the proposed IDS was evaluated using penetration tests on our cyber security test bed. Although the IDS was constructed by the limited features (intervals and length) of packets, the IDS successfully detected cyber-attacks by monitoring the rate of predicted attacking packets.

Machine learning is being used in a wide range of application domains to discover patterns in large datasets. Increasingly, the results of machine learning drive critical decisions in applications related to healthcare and biomedicine. Such health-related applications are often sensitive, and thus, any security breach would be catastrophic. Naturally, the integrity of the results computed by machine learning is of great importance. Recent research has shown that some machine-learning algorithms can be compromised by augmenting their training datasets with malicious data, leading to a new class of attacks called poisoning attacks. Hindrance of a diagnosis may have life-threatening consequences and could cause distrust. On the other hand, not only may a false diagnosis prompt users to distrust the machine-learning algorithm and even abandon the entire system but also such a false positive classification may cause patient distress. In this paper, we present a systematic, algorithm-independent approach for mounting poisoning attacks across a wide range of machine-learning algorithms and healthcare datasets. The proposed attack procedure generates input data, which, when added to the training set, can either cause the results of machine learning to have targeted errors (e.g., increase the likelihood of classification into a specific class), or simply introduce arbitrary errors (incorrect classification). These attacks may be applied to both fixed and evolving datasets. They can be applied even when only statistics of the training dataset are available or, in some cases, even without access to the training dataset, although at a lower efficacy. We establish the effectiveness of the proposed attacks using a suite of six machine-learning algorithms and five healthcare datasets. Finally, we present countermeasures against the proposed generic attacks that are based on tracking and detecting deviations in various accuracy metrics, and benchmark their effectiveness.

Poisoning attack in which an adversary misleads the learning process by manipulating its training set significantly affect the performance of classifiers in security applications. This paper proposed a robust learning method which reduces the influences of attack samples on learning. The sensitivity, defined as the fluctuation of the output with small perturbation of the input, in Localized Generalization Error Model (L-GEM) is measured for each training sample. The classifier's output on attack samples may be sensitive and inaccurate since these samples are different from other untainted samples. An import score is assigned to each sample according to its localized generalization error bound. The classifier is trained using a new training set obtained by resampling the samples according to their importance scores. RBFNN is applied as the classifier in experimental evaluation. The proposed model outperforms than the traditional one under the well-known label flip poisoning attacks including nearest-first and farthest-first flips attack.

With a large number of sensors and control units in networked systems, distributed support vector machines (DSVMs) play a fundamental role in scalable and efficient multi-sensor classification and prediction tasks. However, DSVMs are vulnerable to adversaries who can modify and generate data to deceive the system to misclassification and misprediction. This work aims to design defense strategies for DSVM learner against a potential adversary. We use a game-theoretic framework to capture the conflicting interests between the DSVM learner and the attacker. The Nash equilibrium of the game allows predicting the outcome of learning algorithms in adversarial environments, and enhancing the resilience of the machine learning through dynamic distributed algorithms. We develop a secure and resilient DSVM algorithm with rejection method, and show its resiliency against adversary with numerical experiments.

Despite widespread use of commercial anti-virus products, the number of malicious files detected on home and corporate computers continues to increase at a significant rate. Recently, anti-virus companies have started investing in machine learning solutions to augment signatures manually designed by analysts. A malicious file's determination is often represented as a hierarchical structure consisting of a type (e.g. Worm, Backdoor), a platform (e.g. Win32, Win64), a family (e.g. Rbot, Rugrat) and a family variant (e.g. A, B). While there has been substantial research in automated malware classification, the aforementioned hierarchical structure, which can provide additional information to the classification models, has been ignored. In this paper, we propose the novel idea and study the performance of employing hierarchical learning algorithms for automated classification of malicious files. To the best of our knowledge, this is the first research effort which incorporates the hierarchical structure of the malware label in its automated classification and in the security domain, in general. It is important to note that our method does not require any additional effort by analysts because they typically assign these hierarchical labels today. Our empirical results on a real world, industrial-scale malware dataset of 3.6 million files demonstrate that incorporation of the label hierarchy achieves a significant reduction of 33.1% in the binary error rate as compared to a non-hierarchical classifier which is traditionally used in such problems.

Anti-virus vendors receive hundreds of thousands of malware to be analysed each day. Some are new malware while others are variations or evolutions of existing malware. Because analyzing each malware sample by hand is impossible, automated techniques to analyse and categorize incoming samples are needed. In this work, we explore various machine learning features extracted from malware samples through static analysis for classification of malware binaries into already known malware families. We present a new feature based on control statement shingling that has a comparable accuracy to ordinary opcode n-gram based features while requiring smaller dimensions. This, in turn, results in a shorter training time.

This work targets the automated minimum-energy optimization of Quantized Neural Networks (QNNs) - networks using low precision weights and activations. These networks are trained from scratch at an arbitrary fixed point precision. At iso-accuracy, QNNs using fewer bits require deeper and wider network architectures than networks using higher precision operators, while they require less complex arithmetic and less bits per weights. This fundamental trade-off is analyzed and quantified to find the minimum energy QNN for any benchmark and hence optimize energy-efficiency. To this end, the energy consumption of inference is modeled for a generic hardware platform. This allows drawing several conclusions across different benchmarks. First, energy consumption varies orders of magnitude at iso-accuracy depending on the number of bits used in the QNN. Second, in a typical system, BinaryNets or int4 implementations lead to the minimum energy solution, outperforming int8 networks up to 2-10× at iso-accuracy. All code used for QNN training is available from https://github.com/BertMoons/.

Intrusion detection systems do not perform well when it comes to detecting zero-day attacks, therefore improving their performance in that regard is an active research topic. In this study, to detect zero-day attacks with high accuracy, we proposed two deep learning based anomaly detection models using autoencoder and denoising autoencoder respectively. The key factor that directly affects the accuracy of the proposed models is the threshold value which was determined using a stochastic approach rather than the approaches available in the current literature. The proposed models were tested using the KDDTest+ dataset contained in NSL-KDD, and we achieved an accuracy of 88.28% and 88.65% respectively. The obtained results show that, as a singular model, our proposed anomaly detection models outperform any other singular anomaly detection methods and they perform almost the same as the newly suggested hybrid anomaly detection models.

State-of-the-art convolutional neural networks (ConvNets) are now able to achieve near human performance on a wide range of classification tasks. Unfortunately, current hardware implementations of ConvNets are memory power intensive, prohibiting deployment in low-power embedded systems and IoE platforms. One method of reducing memory power is to exploit the error resilience of ConvNets and accept bit errors under reduced supply voltages. In this paper, we extensively study the effectiveness of this idea and show that further savings are possible by injecting bit errors during ConvNet training. Measurements on an 8KB SRAM in 28nm UTBB FD-SOI CMOS demonstrate supply voltage reduction of 310mV, which results in up to 5.4× leakage power reduction and up to 2.9× memory access power reduction at 99% of floating-point classification accuracy, with no additional hardware cost. To our knowledge, this is the first silicon-validated study on the effect of bit errors in ConvNets.

The evolution of convolutional neural networks (CNNs) into more complex forms of organization, with additional layers, larger convolutions and increasing connections, established the state-of-the-art in terms of accuracy errors for detection and classification challenges in images. Moreover, as they evolved to a point where Gigabytes of memory are required for their operation, we have reached a stage where it becomes fundamental to understand how their inference capabilities can be impaired if data elements somehow become corrupted in memory. This paper introduces fault-injection in these systems by simulating failing bit-cells in hardware memories brought on by relaxing the 100% reliable operation assumption. We analyze the behavior of these networks calculating inference under severe fault-injection rates and apply fault mitigation strategies to improve on the CNNs resilience. For the MNIST dataset, we show that 8x less memory is required for the feature maps memory space, and that in sub-100% reliable operation, fault-injection rates up to 10-1 (with most significant bit protection) can withstand only a 1% error probability degradation. Furthermore, considering the offload of the feature maps memory to an embedded dynamic RAM (eDRAM) system, using technology nodes from 65 down to 28 nm, up to 73 80% improved power efficiency can be obtained.

One of the challenges of malware defense is that the attacker has the advantage over the defender. In many cases, an attack is successful and causes damage before the defender can even begin to prepare a defense. The ability to anticipate attacks and prepare defenses before they occur would be a significant scientific and technological development with practical applications in cybersecurity. In this paper, we present a method to augment machine learning-based malware detection systems by predicting signatures of future malware variants and injecting these variants into the defensive system as a vaccine. Our method uses deep learning to learn patterns of malware evolution from family histories. These evolution patterns are then used to predict future family developments. Our experiments show that a detection system augmented with these future malware signatures is able to detect future malware variants that could not be detected by the detection system alone. In particular, it detected 11 new malware variants without increasing false positives, while providing up to 5 months of lead time between prediction and attack.

The mitigation of insider threats against databases is a challenging problem as insiders often have legitimate access privileges to sensitive data. Therefore, conventional security mechanisms, such as authentication and access control, may be insufficient for the protection of databases against insider threats and need to be complemented with techniques that support real-time detection of access anomalies. The existing real-time anomaly detection techniques consider anomalies in references to the database entities and the amounts of accessed data. However, they are unable to track the access frequencies. According to recent security reports, an increase in the access frequency by an insider is an indicator of a potential data misuse and may be the result of malicious intents for stealing or corrupting the data. In this paper, we propose techniques for tracking users' access frequencies and detecting anomalous related activities in real-time. We present detailed algorithms for constructing accurate profiles that describe the access patterns of the database users and for matching subsequent accesses by these users to the profiles. Our methods report and log mismatches as anomalies that may need further investigation. We evaluated our techniques on the OLTP-Benchmark. The results of the evaluation indicate that our techniques are very effective in the detection of anomalies.

This work describes how automated data generation integrates in a big data pipeline. A lack of veracity in big data can cause models that are inaccurate, or biased by trends in the training data. This can lead to issues as a pipeline matures that are difficult to overcome. This work describes the use of a Generative Adversarial Network to generate sketch data, such as those that might be used in a human verification task. These generated sketches are verified as recognizable using a crowd-sourcing methodology, and finds that the generated sketches were correctly recognized 43.8% of the time, in contrast to human drawn sketches which were 87.7% accurate. This method is scalable and can be used to generate realistic data in many domains and bootstrap a dataset used for training a model prior to deployment.

The pattern recognition in the sparse representation (SR) framework has been very successful. In this model, the test sample can be represented as a sparse linear combination of training samples by solving a norm-regularized least squares problem. However, the value of regularization parameter is always indiscriminating for the whole dictionary. To enhance the group concentration of the coefficients and also to improve the sparsity, we propose a new SR model called adaptive sparse representation classifier(ASRC). In ASRC, a sparse coefficient strengthened item is added in the objective function. The model is solved by the artificial bee colony (ABC) algorithm with variable step to speed up the convergence. Also, a partition strategy for large scale dictionary is adopted to lighten bee's load and removes the irrelevant groups. Through different data sets, we empirically demonstrate the property of the new model and its recognition performance.

Nowadays, an increasing number of IoT vendors have complied and deployed third-party code bases across different architectures. Therefore, to avoid the firmware from being affected by the same known vulnerabilities, searching known vulnerabilities in binary firmware across different architectures is more crucial than ever. However, most of existing vulnerability search methods are limited to the same architecture, there are only a few researches on cross-architecture cases, of which the accuracy is not high. In this paper, to promote the accuracy of existing cross-architecture vulnerability search methods, we propose a new approach based on Support Vector Machine (SVM) and Attributed Control Flow Graph (ACFG) to search known vulnerability in firmware across different architectures at function level. We employ a known vulnerability function to recognize suspicious functions in other binary firmware. First, considering from the internal and external characteristics of the functions, we extract the function level features and basic-block level features of the functions to be inspected. Second, we employ SVM to recognize a little part of suspicious functions based on function level features. After the preliminary screening, we compute the graph similarity between the vulnerability function and suspicious functions based on their ACFGs. We have implemented our approach CVSSA, and employed the training samples to train the model with previous knowledge to improve the accuracy. We also search several vulnerabilities in the real-world firmware images, the experimental results show that CVSSA can be applied to the realistic scenarios.

Support vector machines (SVMs) have been widely used for classification in machine learning and data mining. However, SVM faces a huge challenge in large scale classification tasks. Recent progresses have enabled additive kernel version of SVM efficiently solves such large scale problems nearly as fast as a linear classifier. This paper proposes a new accelerated mini-batch stochastic gradient descent algorithm for SVM classification with additive kernel (AK-ASGD). On the one hand, the gradient is approximated by the sum of a scalar polynomial function for each feature dimension; on the other hand, Nesterov's acceleration strategy is used. The experimental results on benchmark large scale classification data sets show that our proposed algorithm can achieve higher testing accuracies and has faster convergence rate.

In this paper, we propose a new regularization scheme for the well-known Support Vector Machine (SVM) classifier that operates on the training sample level. The proposed approach is motivated by the fact that Maximum Margin-based classification defines decision functions as a linear combination of the selected training data and, thus, the variations on training sample selection directly affect generalization performance. We show that the exploitation of the proposed regularization scheme is well motivated and intuitive. Experimental results show that the proposed regularization scheme outperforms standard SVM in human action recognition tasks as well as classical recognition problems.

Code smells may be introduced in software due to market rivalry, work pressure deadline, improper functioning, skills or inexperience of software developers. Code smells indicate problems in design or code which makes software hard to change and maintain. Detecting code smells could reduce the effort of developers, resources and cost of the software. Many researchers have proposed different techniques like DETEX for detecting code smells which have limited precision and recall. To overcome these limitations, a new technique named as SVMCSD has been proposed for the detection of code smells, based on support vector machine learning technique. Four code smells are specified namely God Class, Feature Envy, Data Class and Long Method and the proposed technique is validated on two open source systems namely ArgoUML and Xerces. The accuracy of SVMCSD is found to be better than DETEX in terms of two metrics, precision and recall, when applied on a subset of a system. While considering the entire system, SVMCSD detect more occurrences of code smells than DETEX.

Network traffic identification has been a hot topic in network security area. The identification of abnormal traffic can detect attack traffic and helps network manager enforce corresponding security policies to prevent attacks. Support Vector Machines (SVMs) are one of the most promising supervised machine learning (ML) algorithms that can be applied to the identification of traffic in IP networks as well as detection of abnormal traffic. SVM shows better performance because it can avoid local optimization problems existed in many supervised learning algorithms. However, as a binary classification approach, SVM needs more research in multiclass classification. In this paper, we proposed an abnormal traffic identification system(ATIS) that can classify and identify multiple attack traffic applications. Each component of ATIS is introduced in detail and experiments are carried out based on ATIS. Through the test of KDD CUP dataset, SVM shows good performance. Furthermore, the comparison of experiments reveals that scaling and parameters has a vital impact on SVM training results.

This paper investigates practical strategies for distributing payload across images with content-adaptive steganography and for pooling outputs of a single-image detector for steganalysis. Adopting a statistical model for the detector's output, the steganographer minimizes the power of the most powerful detector of an omniscient Warden, while the Warden, informed by the payload spreading strategy, detects with the likelihood ratio test in the form of a matched filter. Experimental results with state-of-the-art content-adaptive additive embedding schemes and rich models are included to show the relevance of the results.

Cyber-security threats are a growing concern in networked environments. The development of Intrusion Detection Systems (IDSs) is fundamental in order to provide extra level of security. We have developed an unsupervised anomaly-based IDS that uses statistical techniques to conduct the detection process. Despite providing many advantages, anomaly-based IDSs tend to generate a high number of false alarms. Machine Learning (ML) techniques have gained wide interest in tasks of intrusion detection. In this work, Support Vector Machine (SVM) is deemed as an ML technique that could complement the performance of our IDS, providing a second line of detection to reduce the number of false alarms, or as an alternative detection technique. We assess the performance of our IDS against one-class and two-class SVMs, using linear and non- linear forms. The results that we present show that linear two-class SVM generates highly accurate results, and the accuracy of the linear one-class SVM is very comparable, and it does not need training datasets associated with malicious data. Similarly, the results evidence that our IDS could benefit from the use of ML techniques to increase its accuracy when analysing datasets comprising of non- homogeneous features.

Explosive naval mines pose a threat to ocean and sea faring vessels, both military and civilian. This work applies deep neural network (DNN) methods to the problem of detecting minelike objects (MLO) on the seafloor in side-scan sonar imagery. We explored how the DNN depth, memory requirements, calculation requirements, and training data distribution affect detection efficacy. A visualization technique (class activation map) was incorporated that aids a user in interpreting the model's behavior. We found that modest DNN model sizes yielded better accuracy (98%) than very simple DNN models (93%) and a support vector machine (78%). The largest DNN models achieved textless;1% efficacy increase at a cost of a 17x increase of trainable parameter count and computation requirements. In contrast to DNNs popularized for many-class image recognition tasks, the models for this task require far fewer computational resources (0.3% of parameters), and are suitable for embedded use within an autonomous unmanned underwater vehicle.

Vulnerability being the buzz word in the modern time is the most important jargon related to software and operating system. Since every now and then, software is developed some loopholes and incompleteness lie in the development phase, so there always remains a vulnerability of abruptness in it which can come into picture anytime. Detecting vulnerability is one thing and predicting its occurrence in the due course of time is another thing. If we get to know the vulnerability of any software in the due course of time then it acts as an active alarm for the developers to again develop sound and improvised software the second time. The proposal talks about the implementation of the idea using the artificial neural network, where different data sets are being given as input for being used for further analysis for successful results. As of now, there are models for studying the vulnerabilities in the software and networks, this paper proposal in addition to the current work, will throw light on the predictability of vulnerabilities over the due course of time.