Biblio

Monitoring and managing electric power generation, distribution and transmission requires supervisory control and data acquisition (SCADA) systems. As technology has developed, these systems have become huge, complicated, and distributed, which makes them susceptible to new risks. In particular, the lack of security in SCADA systems make them a target for network attacks such as denial of service (DoS) and developing solutions for this issue is the main objective of this thesis. By reviewing various existing system solutions for securing SCADA systems, a new security approach is recommended that employs Artificial Intelligence(AI). AI is an innovative approach that imparts learning ability to software. Here deep learning algorithms and machine learning algorithms are used to develop an intrusion detection system (IDS) to combat cyber-attacks. Various methods and algorithms are evaluated to obtain the best results in intrusion detection. The results reveal the Bi-LSTM IDS technique provides the highest intrusion detection (ID) performance compared with previous techniques to secure SCADA systems

In this work a time evolution model is used to help categorize malicious samples. This method can be used in anti-malware testing procedures as well as in detecting cyber-attacks. The time evolution mathematical model can help security experts to better understand the behaviour of malware attacks and malware families. It can be used for estimating much better their spreading and for planning the required defence actions against them. The basic time dependent variable of this model is the Ratio of the malicious files within an investigated time window. To estimate the main characteristics of the time series describing the change of the Ratio values related to a specific malicious file, nonlinear, exponential curve fitting method is used. The free parameters of the model were determined by numerical searching algorithms. The three parameters can be used in the information security field to describe more precisely the behaviour of a piece of malware and a family of malware as well. In the case of malware families, the aggregation of these parameters can provide effective solution for estimating the cyberthreat trends.

Distributed Denial of Service (DDoS) attacks pose a considerable threat to Cloud Computing, Internet of Things (IoT) and other services offered on the Internet. The victim server receives terabytes of data per second during the DDoS attack. It may take hours to examine them to detect a potential threat, leading to denial of service to legitimate users. Processing vast volumes of traffic to mitigate the attack is a challenging task for network administrators. High-performance techniques are more suited for processing DDoS attack traffic compared to Sequential Processing Techniques. This paper proposes a Multi-Core Parallel Processing Technique to prepare the time series data for the early detection of DDoS flooding attacks. Different time series analysis methods are suggested to detect the attack early on. Producing time series data using parallel processing saves time and further speeds up the detection of the attack. The proposed method is applied to the benchmark data set CICDDoS2019 for generating four different time series to detect TCP-based flooding attacks, namely TCP-SYN, TCP-SYN-ACK, TCP-ACK, and TCP-RST. The implementation results show that the proposed method can give a speedup of 2.3 times for processing attack traffic compared to sequential processing.

With the rapid development of the Internet, cyberspace security has become a potentially huge problem. At the same time, the disclosure of cyberspace vulnerabilities is getting faster and faster. Traditional protection methods based on known features cannot effectively defend against new network attacks. Network attack is no more a single vulnerability exploit, but an APT attack based on multiple complicated methods. Cyberspace attacks have become ``rationalized'' on the surface. Currently, there are a lot of researches about visualization of attack paths, but there is no an overall plan to reproduce the attack path. Most researches focus on the detection and characterization individual based on single behavior cyberspace attacks, which loose it's abilities to help security personnel understand the complete attack behavior of attackers. The key factors of this paper is to collect the attackers' aggressive behavior by reverse retrospective method based on the actual shooting range environment. By finding attack nodes and dividing offensive behavior into time series, we can characterize the attacker's behavior path vividly and comprehensively.

In recent years, biometric authentication, such as fingerprint and face recognition, has become widespread in smartphones. However, fingerprint and face authentication have the problem that they cannot be used depending on the condition of the user's fingers or face. Therefore, we have been investigating a new biometric authentication system using pinna as a personal authentication system for smart phones. We have studied a personal authentication system using the Pinna Related Transfer Function (PRTF), which is an acoustic transfer function measured from the pinna. However, since the position of the smartphone changes every time it is placed on the ear, there is a problem that the authentication rate decreases. In this paper, we propose a multimodal personal authentication system using PRTF, pinna images, and smartphone location information, and verify its effectiveness. The results show that the proposed authentication system can improve the robustness against the fluctuation of the smartphone location.

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 progressive expansion of renewable energies, especially wind power plants being promoted in Germany as part of the energy transition, places new demands on the transmission grid. As an alternative to grid expansion, sector coupling of the gas and electricity sector through Power-to-Gas (PtG) technology is seen as a great opportunity to make the energy transmission more flexible and reliable in the future as well as make use of already existing gas infrastructure. In this paper, PtG plants are dimensioned and placed in a model of the German transmission grid. Time series based load flow calculations are performed allowing conclusions about the line loading for the exemplary year 2016.

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.

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.

Trustworthiness is a soft-security feature that evaluates the correct behavior of nodes in a network. More specifically, this feature tries to answer the following question: how much should we trust in a certain node? To determine the trustworthiness of a node, our approach focuses on two reputation indicators: the self-data trust, which evaluates the data generated by the node itself taking into account its historical data; and the peer-data trust, which utilizes the nearest nodes' data. In this paper, we show how these two indicators can be calculated using the Gaussian Overlap and Pearson correlation. This paper includes a validation of our trustworthiness approach using real data from unofficial and official weather stations in Portugal. This is a representative scenario of the current situation in many other areas, with different entities providing different kinds of data using autonomous sensors in a continuous way over the networks.

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.

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.

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.

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.

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.

Proposed an approach for information security breaches detection in distributed control systems based on prediction of multidimensional time series formed of sensor and actuator data.

Cyber defense can no longer be limited to intrusion detection methods. These systems require malicious activity to enter an internal network before an attack can be detected. Having advanced, predictive knowledge of future attacks allow a potential victim to heighten security and possibly prevent any malicious traffic from breaching the network. This paper investigates the use of Auto-Regressive Integrated Moving Average (ARIMA) models and Bayesian Networks (BN) to predict future cyber attack occurrences and intensities against two target entities. In addition to incident count forecasting, categorical and binary occurrence metrics are proposed to better represent volume forecasts to a victim. Different measurement periods are used in time series construction to better model the temporal patterns unique to each attack type and target configuration, seeing over 86% improvement over baseline forecasts. Using ground truth aggregated over different measurement periods as signals, a BN is trained and tested for each attack type and the obtained results provided further evidence to support the findings from ARIMA. This work highlights the complexity of cyber attack occurrences; each subset has unique characteristics and is influenced by a number of potential external factors.

Web attacks have increased rapidly in recent years. However, traditional methods are useless to track web attackers. Browser fingerprint, as a stateless tracking technique, can be used to solve this problem. Given browser fingerprint changes easily and frequently, it is easy to lose track. Therefore, we need to improve the stability of browser fingerprint by linking the new one to the previous chain. In this paper, we propose LSTM model to learn the potential relationship of browser fingerprint evolution. In addition, we adjust the input feature vector to time series and construct training set to train the model. The results show that our model can construct the tracking chain perfectly well with average ownership up to 99.3%.

The IRC botnet is the earliest and most significant botnet group that has a significant impact. Its characteristic is to control multiple zombies hosts through the IRC protocol and constructing command control channels. Relevant research analyzes the large amount of network traffic generated by command interaction between the botnet client and the C&C server. Packet capture traffic monitoring on the network is currently a more effective detection method, but this information does not reflect the essential characteristics of the IRC botnet. The increase in the amount of erroneous judgments has often occurred. To identify whether the botnet control server is a homogenous botnet, dynamic network communication characteristic curves are extracted. For unequal time series, dynamic time warping distance clustering is used to identify the homologous botnets by category, and in order to improve detection. Speed, experiments will use SAX to reduce the dimension of the extracted curve, reducing the time cost without reducing the accuracy.

To identify potential risks to the system security presented by time series it is offered to use wavelet analysis, the indicator of time-and-frequency distribution, the correlation analysis of wavelet-spectra for receiving rather complete range of data about the process studied. The indicator of time-and-frequency localization of time series was proposed allowing to estimate the speed of non-stationary changing. The complex approach is proposed to use the wavelet analysis, the time-and-frequency distribution of time series and the wavelet spectra correlation analysis; this approach contributes to obtaining complete information on the studied phenomenon both in numerical terms, and in the form of visualization for identifying and predicting potential system security threats.

The recently developed deep belief network (DBN) has been shown to be an effective methodology for solving time series forecasting problems. However, the performance of DBN is seriously depended on the reasonable setting of hyperparameters. At present, random search, grid search and Bayesian optimization are the most common methods of hyperparameters optimization. As an alternative, a state-of-the-art derivative-free optimizer-negative correlation search (NCS) is adopted in this paper to decide the sizes of DBN and learning rates during the training processes. A comparative analysis is performed between the proposed method and other popular techniques in the time series forecasting experiment based on two types of time series datasets. Experiment results statistically affirm the efficiency of the proposed model to obtain better prediction results compared with conventional neural network models.

The prevalence of mobile devices and location-based services (LBS) has generated great concerns regarding the LBS users' privacy, which can be compromised by statistical analysis of their movement patterns. A number of algorithms have been proposed to protect the privacy of users in such systems, but the fundamental underpinnings of such remain unexplored. Recently, the concept of perfect location privacy was introduced and its achievability was studied for anonymization-based LBS systems, where user identifiers are permuted at regular intervals to prevent identification based on statistical analysis of long time sequences. In this paper, we significantly extend that investigation by incorporating the other major tool commonly employed to obtain location privacy: obfuscation, where user locations are purposely obscured to protect their privacy. Since anonymization and obfuscation reduce user utility in LBS systems, we investigate how location privacy varies with the degree to which each of these two methods is employed. We provide: (1) achievability results for the case where the location of each user is governed by an i.i.d. process; (2) converse results for the i.i.d. case as well as the more general Markov Chain model. We show that, as the number of users in the network grows, the obfuscation-anonymization plane can be divided into two regions: in the first region, all users have perfect location privacy; and, in the second region, no user has location privacy.

Vehicular Ad Hoc Networks (VANETs) enable vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications that bring many benefits and conveniences to improve the road safety and drive comfort in future transportation systems. Sybil attack is considered one of the most risky threats in VANETs since a Sybil attacker can generate multiple fake identities with false messages to severely impair the normal functions of safety-related applications. In this paper, we propose a novel Sybil attack detection method based on Received Signal Strength Indicator (RSSI), Voiceprint, to conduct a widely applicable, lightweight and full-distributed detection for VANETs. To avoid the inaccurate position estimation according to predefined radio propagation models in previous RSSI-based detection methods, Voiceprint adopts the RSSI time series as the vehicular speech and compares the similarity among all received time series. Voiceprint does not rely on any predefined radio propagation model, and conducts independent detection without the support of the centralized infrastructure. It has more accurate detection rate in different dynamic environments. Extensive simulations and real-world experiments demonstrate that the proposed Voiceprint is an effective method considering the cost, complexity and performance.