Biblio

A comparative analysis of the classical and approximation methods of spectral analysis of fast-variable processes in technical systems is carried out. It is shown that the approximation methods make it possible to substantially remove the contradiction between the requirements for spectrum smoothing and its frequency resolution. On practical examples of vibroacoustic signals, the effectiveness of approximation methods is shown. The Prony method was used to process the time series. The interactive frequency segmentation method and the direct identification method were used for approximation and frequency characteristics.

With the popularity of smart devices in the power grid and the advancement of data collection technology, the amount of electricity usage data has exploded in recent years, which is beneficial for optimizing service quality and grid operation. However, current data analysis is mainly based on cloud platforms, which poses challenges to transmission bandwidth, computing resources, and transmission delays. To solve the problem, this paper proposes a graph convolution neural networks (GCNs) based edge-cloud collaborative anomaly detection model. Specifically, the time series is converted into graph data based on visibility graph model, and graph convolutional network model is adopted to classify the labeled graph data for anomaly detection. Then a model segmentation method is proposed to adaptively divide the anomaly detection model between the edge equipment and the back-end server. Experimental results show that the proposed scheme provides an effective solution to edge anomaly detection and can make full use of the computing resources of terminal equipment.

The continuous change of communication frequency brings difficulties to the reconnaissance and prediction of non-cooperative communication. The core of this communication process is the frequency-hopping (FH) sequence with pseudo-random characteristics, which controls carrier frequency hopping. However, FH sequence is always generated by a certain model and is a kind of time sequence with certain regularity. Long Short-Term Memory (LSTM) neural network in deep learning has been proved to have strong ability to solve time series problems. Therefore, in this paper, we establish LSTM model to implement FH sequence prediction. The simulation results show that LSTM-based scheme can effectively predict frequency point by point based on historical HF frequency data. Further, we achieve frequency interval prediction based on frequency point prediction.

The pervasiveness of personalized collaborative recommender systems has shown the powerful capability in a wide range of E-commerce services such as Amazon, TripAdvisor, Yelp, etc. However, fundamental vulnerabilities of collaborative recommender systems leave space for malicious users to affect the recommendation results as the attackers desire. A vast majority of existing detection methods assume certain properties of malicious attacks are given in advance. In reality, improving the detection performance is usually constrained due to the challenging issues: (a) various types of malicious attacks coexist, (b) limited representations of malicious attack behaviors, and (c) practical evidences for exploring and spotting anomalies on real-world data are scarce. In this paper, we investigate a unified detection framework in an eye for an eye manner without being bothered by the details of the attacks. Firstly, co-visitation and co-rating graphs are constructed using association rules. Then, attribute representations of nodes are empirically developed from the perspectives of linkage pattern, structure-based property and inherent association of nodes. Finally, both attribute information and connective coherence of graph are combined in order to infer suspicious nodes. Extensive experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks. Additionally, abnormality forensics metrics including distribution of rating intention, time aggregation of suspicious ratings, degree distributions before as well as after removing suspicious nodes and time series analysis of historical ratings, are provided so as to discover interesting findings such as suspicious nodes (items or ratings) on real-world data.

Reliability analysis of concurrent data based on Botnet modeling is conducted in this paper. At present, the detection methods for botnets are mainly focused on two aspects. The first type requires the monitoring of high-privilege systems, which will bring certain security risks to the terminal. The second type is to identify botnets by identifying spam or spam, which is not targeted. By introducing multi-dimensional permutation entropy, the impact of permutation entropy on the permutation entropy is calculated based on the data communicated between zombies, describing the complexity of the network traffic time series, and the clustering variance method can effectively solve the difficulty of the detection. This paper is organized based on the data complex structure analysis. The experimental results show acceptable performance.

Inferring behavior model of a running software system is quite useful for several automated software engineering tasks, such as program comprehension, anomaly detection, and testing. Most existing dynamic model inference techniques are white-box, i.e., they require source code to be instrumented to get run-time traces. However, in many systems, instrumenting the entire source code is not possible (e.g., when using black-box third-party libraries) or might be very costly. Unfortunately, most black-box techniques that detect states over time are either univariate, or make assumptions on the data distribution, or have limited power for learning over a long period of past behavior. To overcome the above issues, in this paper, we propose a hybrid deep neural network that accepts as input a set of time series, one per input/output signal of the system, and applies a set of convolutional and recurrent layers to learn the non-linear correlations between signals and the patterns, over time. We have applied our approach on a real UAV auto-pilot solution from our industry partner with half a million lines of C code. We ran 888 random recent system-level test cases and inferred states, over time. Our comparison with several traditional time series change point detection techniques showed that our approach improves their performance by up to 102%, in terms of finding state change points, measured by F1 score. We also showed that our state classification algorithm provides on average 90.45% F1 score, which improves traditional classification algorithms by up to 17%.

To ensure quality of service and user experience, large Internet companies often monitor various Key Performance Indicators (KPIs) of their systems so that they can detect anomalies and identify failure in real time. However, due to a large number of various KPIs and the lack of high-quality labels, existing KPI anomaly detection approaches either perform well only on certain types of KPIs or consume excessive resources. Therefore, to realize generic and practical KPI anomaly detection in the real world, we propose a KPI anomaly detection framework named iRRCF-Active, which contains an unsupervised and white-box anomaly detector based on Robust Random Cut Forest (RRCF), and an active learning component. Specifically, we novelly propose an improved RRCF (iRRCF) algorithm to overcome the drawbacks of applying original RRCF in KPI anomaly detection. Besides, we also incorporate the idea of active learning to make our model benefit from high-quality labels given by experienced operators. We conduct extensive experiments on a large-scale public dataset and a private dataset collected from a large commercial bank. The experimental resulta demonstrate that iRRCF-Active performs better than existing traditional statistical methods, unsupervised learning methods and supervised learning methods. Besides, each component in iRRCF-Active has also been demonstrated to be effective and indispensable.

Network covert timing channel(NCTC) is a process of transmitting hidden information by means of inter-packet delay (IPD) of legitimate network traffic. Their ability to evade traditional security policies makes NCTCs a grave security concern. However, a robust method that can be used to detect a large number of NCTCs is missing. In this paper, a NCTC detection method based on chaos theory and threshold secret sharing is proposed. Our method uses chaos theory to reconstruct a high-dimensional phase space from one-dimensional time series and extract the unique and stable channel traits. Then, a channel identifier is constructed using the secret reconstruction strategy from threshold secret sharing to realize the mapping of the channel features to channel identifiers. Experimental results show that the approach can detect varieties of NCTCs with a guaranteed true positive rate and greatly improve the versatility and robustness.

This paper explores using chaos-based cryptography for transmitting multimedia data, mainly speech and voice messages, over public communication channels, such as the internet. The secret message to be transmitted is first converted into a one-dimensional time series, that can be cast in a digital/binary format. The main feature of the proposed technique is mapping the two levels of every corresponding bit of the time series into different multiple chaotic orbits, using a simple encryption function. This one-to-many mapping robustifies the encryption technique and makes it resilient to crypto-analysis methods that rely on associating the energy level of the signal into two binary levels, using return map attacks. A chaotic nonautonomous Duffing oscillator is chosen to implement the suggested technique, using three different parameters that are assumed unknown at the receiver side. Synchronization between the transmitter and the receiver and reconstructing the secret message, at the receiver side, is done using a Lyapunov-based adaptive technique. Achieving stable operation, tuning the required control gains, as well as effective utilization of the bandwidth of the public communication channel are investigated. Two different case studies are presented; the first one deals with text that can be expressed as 8-bit ASCII code, while the second one corresponds to an analog acoustic signal that corresponds to the voice associated with pronouncing a short sentence. Advantages and limitation of the proposed technique are highlighted, while suggesting extensions to other multimedia signals, along with their required additional computational effort.

We define discounted differential privacy, as an alternative to (conventional) differential privacy, to investigate privacy of evolving datasets, containing time series over an unbounded horizon. We use privacy loss as a measure of the amount of information leaked by the reports at a certain fixed time. We observe that privacy losses are weighted equally across time in the definition of differential privacy, and therefore the magnitude of privacy-preserving additive noise must grow without bound to ensure differential privacy over an infinite horizon. Motivated by the discounted utility theory within the economics literature, we use exponential and hyperbolic discounting of privacy losses across time to relax the definition of differential privacy under continual observations. This implies that privacy losses in distant past are less important than the current ones to an individual. We use discounted differential privacy to investigate privacy of evolving datasets using additive Laplace noise and show that the magnitude of the additive noise can remain bounded under discounted differential privacy. We illustrate the quality of privacy-preserving mechanisms satisfying discounted differential privacy on smart-meter measurement time-series of real households, made publicly available by Ausgrid (an Australian electricity distribution company).

Jamming attacks target a wireless network creating an unwanted denial of service. 5G is vulnerable to these attacks despite its resilience prompted by the use of millimeter wave bands. Over the last decade, several types of jamming detection techniques have been proposed, including fuzzy logic, game theory, channel surfing, and time series. Most of these techniques are inefficient in detecting smart jammers. Thus, there is a great need for efficient and fast jamming detection techniques with high accuracy. In this paper, we compare the efficiency of several machine learning models in detecting jamming signals. We investigated the types of signal features that identify jamming signals, and generated a large dataset using these parameters. Using this dataset, the machine learning algorithms were trained, evaluated, and tested. These algorithms are random forest, support vector machine, and neural network. The performance of these algorithms was evaluated and compared using the probability of detection, probability of false alarm, probability of miss detection, and accuracy. The simulation results show that jamming detection based random forest algorithm can detect jammers with a high accuracy, high detection probability and low probability of false alarm.

In the process of informationization and networking of smart grids, the original physical isolation was broken, potential risks increased, and the increasingly serious cyber security situation was faced. Therefore, it is critical to develop accuracy and efficient anomaly detection methods to disclose various threats. However, in the industry, mainstream security devices such as firewalls are not able to detect and resist some advanced behavior attacks. In this paper, we propose a time series anomaly detection model, which is based on the periodic extraction method of discrete Fourier transform, and determines the sequence position of each element in the period by periodic overlapping mapping, thereby accurately describe the timing relationship between each network message. The experiments demonstrate that our model can detect cyber attacks such as man-in-the-middle, malicious injection, and Dos in a highly periodic network.

Over the years, technology has reformed the perception of the world related to security concerns. To tackle security problems, we proposed a system capable of detecting security alerts. System encompass audio events that occur as an outlier against background of unusual activity. This ambiguous behaviour can be handled by auditory classification. In this paper, we have discussed two techniques of extracting features from sound data including: time-based and signal based features. In first technique, we preserve time-series nature of sound, while in other signal characteristics are focused. Convolution neural network is applied for categorization of sound. Major aim of research is security challenges, so we have generated data related to surveillance in addition to available datasets such as UrbanSound 8k and ESC-50 datasets. We have achieved 94.6% accuracy for proposed methodology based on self-generated dataset. Improved accuracy on locally prepared dataset demonstrates novelty in research.

Cyber breaches can result in disruption to business operations, reputation damage as well as directly affecting the financial stability of the targeted corporations, with potential impacts on future profits and stock values. Automatic network-stream monitoring becomes necessary for cyber situation awareness, and time-series anomaly detection plays an important role in network stream monitoring. This study surveyed recent research on time-series analysis methods in respect of parametric and non-parametric techniques, and popular machine learning platforms for data analysis on streaming data on both single server and cloud computing environments. We believe it provides a good reference for researchers in both academia and industry to select suitable (time series) data analysis techniques, and computing platforms, dependent on the data scale and real-time requirements.

The internet of things (IoT) is the popular wireless network for data collection applications. The IoT networks are deployed in dense or sparse architectures, out of which the dense networks are vastly popular as these are capable of gathering the huge volumes of data. The collected data is analyzed using the historical or continuous analytical systems, which uses the back testing or time-series analytics to observe the desired patterns from the target data. The lost or bad interval data always carries the high probability to misguide the analysis reports. The data is lost due to a variety of reasons, out of which the most popular ones are associated with the node failures and connectivity holes, which occurs due to physical damage, software malfunctioning, blackhole/wormhole attacks, route poisoning, etc. In this paper, the work is carried on the new routing scheme for the IoTs to avoid the connectivity holes, which analyzes the activity of wireless nodes and takes the appropriate actions when required.

Low power and lossy network (LLN) comprising of constrained devices like sensors and RFIDs, is a major component in the Internet of Things (IoT) environment as these devices provide global connectivity to physical devices or “Things”. LLNs are tied to the Internet or any High Performance Computing environment via an adaptation layer called 6LoWPAN (IPv6 over Low power Personal Area Network). The routing protocol used by 6LoWPAN is RPL (IPv6 Routing Protocol over LLN). Like many other routing protocols, RPL is susceptible to blackhole attacks which cause topological isolation for a subset of nodes in the LLN. A malicious node instigating the blackhole attack drops received packets from nodes in its subtree which it is supposed to forward. Thus, the malicious node successfully isolates nodes in its subtree from the rest of the network. In this paper, we propose an algorithm based on the concept of exponential smoothing to detect the topological isolation of nodes due to blackhole attack. Exponential smoothing is a technique for smoothing time series data using the exponential window function and is used for short, medium and long term forecasting. In our proposed algorithm, exponential smoothing is used to estimate the next arrival time of packets at the sink node from every other node in the LLN. Using this estimation, the algorithm is designed to identify the malicious nodes instigating blackhole attack in real time.

Continuous growth in sensor data and other temporal sequence data necessitates efficient retrieval and similarity search support on these big time series datasets. However, finding exact similarity results, especially at the granularity of subsequences, is known to be prohibitively costly for large data sets. In this paper, we thus propose an efficient framework for solving this exact subsequence similarity match problem, called TINN (TIme series Nearest Neighbor search). Exploiting the range interval diversity properties of time series datasets, TINN captures similarity at two levels of abstraction, namely, relationships among subsequences within each long time series and relationships across distinct time series in the data set. These relationships are compactly organized in an augmented relationship graph model, with the former relationships encoded in similarity vectors at TINN nodes and the later captured by augmented edge types in the TINN Graph. Query processing strategy deploy novel pruning techniques on the TINN Graph, including node skipping, vertical and horizontal pruning, to significantly reduce the number of time series as well as subsequences to be explored. Comprehensive experiments on synthetic and real world time series data demonstrate that our TINN model consistently outperforms state-of-the-art approaches while still guaranteeing to retrieve exact matches.

Hydraulic systems is a class of nonlinear complex systems. There are many typical characteristics with the systems: multiple functional components, multiple operation modes, space-time coupling work, and monitoring signals for faults are multivariate time series data, etc. Because of the characteristics, fault diagnosis for Hydraulic systems is not easy. Traditional fault diagnosis methods mostly ignore the multivariable timing characteristics of monitoring signals, it has made many detection and diagnosis (especially for multiple fault) can not keep high accuracy, and some of the methods are not even be able to multiple fault diagnosis. Aim at the problem, a multivariate time series classification based diagnosis method is proposed. Firstly, extracting timing characteristics (transformed features) from the time series data collected via sensors by 1-NN method. Secondly, training the transformed features by multi-class OVO-SVM to classify multivariate time series. Simulation of the method contains single fault and multiple faults conditions, the results show that the method has high accuracy, it can complete multiple-faults classification.

This paper describes the technology of neural network application to solve the problem of information security incidents forecasting. We describe the general problem of analyzing and predicting time series in a graphical and mathematical setting. To solve this problem, it is proposed to use a neural network model. To solve the task of forecasting a time series of information security incidents, data are generated and described on the basis of which the neural network is trained. We offer a neural network structure, train the neural network, estimate it's adequacy and forecasting ability. We show the possibility of effective use of a neural network model as a part of an intelligent forecasting system.

This paper provides an approach to the detection of information security breaches in automated process control systems (APCS), which consists in forecasting multivariate time series formed from the values of the operating parameters of the end system devices. Using an experimental model of water treatment, a comparison was made of the forecasting results for the parameters characterizing the operation of the entire model, and for the parameters characterizing the flow of individual subprocesses implemented by the model. For forecasting, GRU-neural network training was performed.

The denial-of-service (DoS) attack is a very common type of cyber attack that can affect critical cyber-physical systems, such as smart grids, by hampering the monitoring and control of the system, for example, creating unavailability of data from the attacked zone. While developing countermeasures can help reduce such risks, it is essential to develop techniques to recover from such scenarios if they occur by estimating the state of the system. Considering the continuous data-stream from the PMUs as time series, this work exploits the bus-to-bus cross-correlations to estimate the state of the system's components under attack using the PMU data of the rest of the buses. By applying this technique, the state of the power system can be estimated under various DoS attack sizes with great accuracy. The estimation accuracy in terms of the mean squared error (MSE) has been used to identify the relative vulnerability of the PMUs of the grid and the most vulnerable time for the DoS attack.

Capturing the patterns in adversarial movement can present crucial insight into team dynamics and organization of cybercrimes. This information can be used for additional assessment and comparison of decision making approaches during cyberattacks. In this study, we propose a data-driven analysis based on time series analysis and social networks to identify patterns and alterations in time allocated to intrusion stages and adversarial movements. The results of this analysis on two case studies of collegiate cybersecurity exercises is provided as well as an analytical comparison of their behavioral trends and characteristics. This paper presents preliminary insight into complexities of individual and group level adversarial movement and decision-making as cyberattacks unfold.

The Internet has gradually penetrated into the national economy, politics, culture, military, education and other fields. Due to its openness, interconnectivity and other characteristics, the Internet is vulnerable to all kinds of malicious attacks. The research uses a honeynet to collect attacker information, and proposes a network penetration recognition technology based on interactive behavior analysis. Using Sebek technology to capture the attacker's keystroke record, time series modeling of the keystroke sequences of the interaction behavior is proposed, using a Recurrent Neural Network. The attack recognition method is constructed by using Long Short-Term Memory that solves the problem of gradient disappearance, gradient explosion and long-term memory shortage in ordinary Recurrent Neural Network. Finally, the experiment verifies that the short-short time memory network has a high accuracy rate for the recognition of penetration attacks.

The anomaly detection of time series is a hotspot of time series data mining. The own characteristics of different anomaly detectors determine the abnormal data that they are good at. There is no detector can be optimizing in all types of anomalies. Moreover, it still has difficulties in industrial production due to problems such as a single detector can't be optimized at different time windows of the same time series. This paper proposes an adaptive model based on time series characteristics and selecting appropriate detector and run-time parameters for anomaly detection, which is called ATSDLN(Adaptive Time Series Detector Learning Network). We take the time series as the input of the model, and learn the time series representation through FCN. In order to realize the adaptive selection of detectors and run-time parameters according to the input time series, the outputs of FCN are the inputs of two sub-networks: the detector selection network and the run-time parameters selection network. In addition, the way that the variable layer width design of the parameter selection sub-network and the introduction of transfer learning make the model be with more expandability. Through experiments, it is found that ATSDLN can select appropriate anomaly detector and run-time parameters, and have strong expandability, which can quickly transfer. We investigate the performance of ATSDLN in public data sets, our methods outperform other methods in most cases with higher effect and better adaptation. We also show experimental results on public data sets to demonstrate how model structure and transfer learning affect the effectiveness.

The greatest threat towards securing the organization and its assets are no longer the attackers attacking beyond the network walls of the organization but the insiders present within the organization with malicious intent. Existing approaches helps to monitor, detect and prevent any malicious activities within an organization's network while ignoring the human behavior impact on security. In this paper we have focused on user behavior profiling approach to monitor and analyze user behavior action sequence to detect insider threats. We present an ensemble hybrid machine learning approach using Multi State Long Short Term Memory (MSLSTM) and Convolution Neural Networks (CNN) based time series anomaly detection to detect the additive outliers in the behavior patterns based on their spatial-temporal behavior features. We find that using Multistate LSTM is better than basic single state LSTM. The proposed method with Multistate LSTM can successfully detect the insider threats providing the AUC of 0.9042 on train data and AUC of 0.9047 on test data when trained with publically available dataset for insider threats.