Biblio

Remotely connected devices have been adopted in several industrial control systems (ICS) recently due to the advancement in the Industrial Internet of Things (IIoT). This led to new security vulnerabilities because of the expansion of the attack surface. Moreover, cybersecurity incidents in critical infrastructures are increasing. In the ICS, RS-485 cables are widely used in its network for serial communication between each component. However, almost 30 years ago, most of the industrial network protocols implemented over RS-485 such as Modbus were designed without security features. Therefore, anomaly detection is required in industrial control networks to secure communication in the systems. The goal of this paper is to study unsupervised anomaly detection in RS-485 traffic using autoencoders. Five threat scenarios in the physical layer of the industrial control network are proposed. The novelty of our method is that RS-485 traffic is collected indirectly by an analog-to-digital converter. In the experiments, multilayer perceptron (MLP), 1D convolutional, Long Short-Term Memory (LSTM) autoencoders are trained to detect anomalies. The results show that three autoencoders effectively detect anomalous traffic with F1-scores of 0.963, 0.949, and 0.928 respectively. Due to the indirect traffic collection, our method can be practically applied in the industrial control network.

OHODIN is an online extension for data streams of the kNN-based ODIN anomaly detection approach. It provides a detection-threshold heuristic that is based on extreme value theory. In contrast to sophisticated anomaly and novelty detection approaches the decision-making process of ODIN is interpretable by humans, making it interesting for certain applications. However, it is limited in terms of the underlying detection method. In this article, we present an extension of the OHODIN to further detection techniques to reinforce OHODIN capability of online data streams anomaly detection. We introduce the algorithm modifications and an experimental evaluation with competing state-of-the-art anomaly detection approaches.

Supervisory control and data acquisition (SCADA) systems are used with monitoring and control purposes for the process not to fail in industrial control systems. Today, the increase in the use of standard protocols, hardware, and software in the SCADA systems that can connect to the internet and institutional networks causes these systems to become a target for more cyber-attacks. Intrusion detection systems are used to reduce or minimize cyber-attack threats. The use of deep learning-based intrusion detection systems also increases in parallel with the increase in the amount of data in the SCADA systems. The unsupervised feature learning present in the deep learning approaches enables the learning of important features within the large datasets. The features learned in an unsupervised way by using deep learning techniques are used in order to classify the data as normal or abnormal. Architectures such as convolutional neural network (CNN), Autoencoder (AE), deep belief network (DBN), and long short-term memory network (LSTM) are used to learn the features of SCADA data. These architectures use softmax function, extreme learning machine (ELM), deep belief networks, and multilayer perceptron (MLP) in the classification process. In this study, anomaly-based intrusion detection systems consisting of convolutional neural network, autoencoder, deep belief network, long short-term memory network, or various combinations of these methods on the SCADA networks in the literature were analyzed and the positive and negative aspects of these approaches were explained through their attack detection performances.

System logs record valuable information about the runtime status of IT systems. Therefore, system logs are a naturally excellent source of information for anomaly detection. Most of the existing studies on log-based anomaly detection construct a detection model to identify anomalous logs. Generally, the model treats historical logs as natural language sequences and learns the normal patterns from normal log sequences, and detects deviations from normal patterns as anomalies. However, the majority of existing methods focus on sequential and quantitative information and ignore semantic information hidden in log sequence so that they are inefficient in anomaly detection. In this paper, we propose a novel framework for automatically detecting log anomalies by utilizing an attention-based Bi-LSTM model. To demonstrate the effectiveness of our proposed model, we evaluate the performance on a public production log dataset. Extensive experimental results show that the proposed approach outperforms all comparison methods for anomaly detection.

Bitcoin has received a lot of attention from investors, researchers, regulators, and the media. It is a known fact that the Bitcoin price usually fluctuates greatly. However, not enough scientific research has been done on these fluctuations. In this study, long short-term memory (LSTM) modeling from Recurrent Neural Networks, which is one of the deep learning methods, was applied on Bitcoin values. As a result of this application, anomaly detection was carried out in the values from the data set. With the LSTM network, a time-dependent representation of Bitcoin price can be captured, and anomalies can be selected. The factors that play a role in the formation of the model to be applied in the detection of anomalies with the experimental results were evaluated.

Due to immense need for implementing security measures and control ongoing activities, intelligent video analytics is regarded as one of the outstanding and challenging research domains in Computer Vision. Assigning video operator to manually monitor the surveillance videos 24×7 to identify occurrence of interesting and anomalous events like robberies, wrong U-turns, violence, accidents is cumbersome and error- prone. Therefore, to address the issue of continuously monitoring surveillance videos and detect the anomalies from them, a deep learning approach based on pipelined sequence of convolutional autoencoder and sequence to sequence long short-term memory autoencoder has been proposed. Specifically, unsupervised learning approach encompassing one-class classification paradigm has been proposed for detection of anomalies in videos. The effectiveness of the propped model is demonstrated on benchmarked anomaly detection dataset and significant results in terms of equal error rate, area under curve and time required for detection have been achieved.

Testing or defending the security of a large network can be challenging because of the sheer number of potential ingress points that need to be investigated and evaluated for vulnerabilities. In short, manual security testing and analysis do not easily scale to large networks. While it has been shown that clustering can simplify the problem somewhat, the data structures and formats returned by the latest network mapping tools are not conducive to clustering algorithms. In this paper we introduce a hybrid similarity algorithm to compute the distance between two network services and then use those calculations to support a clustering algorithm designed to compress a large network attack surface by orders of magnitude. Doing so allows for new testing strategies that incorporate outlier detection and smart consolidation of test cases to improve accuracy and timeliness of testing. We conclude by presenting two case studies using an organization's network attack surface data to demonstrate the effectiveness of this approach.

Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people’s lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection.

In recent years, Deep Learning (DL) has been utilized for cyber-attack detection mechanisms as it offers highly accurate detection and is able to overcome the limitations of standard machine learning techniques. When applied in a Software-Defined Network (SDN) environment, a DL-based detection mechanism shows satisfying detection performance. However, in the case of adversarial attacks, the detection performance deteriorates. Therefore, in this paper, first, we outline a highly accurate flooding DDoS attack detection framework based on DL for SDN environments. Second, we investigate the performance degradation of our detection framework when being tested with two adversary traffic datasets. Finally, we evaluate three adversarial training procedures for improving the detection performance of our framework concerning adversarial attacks. It is shown that the application of one of the adversarial training procedures can avoid detection performance degradation and thus might be used in a real-time detection system based on continual learning.

Ensuring the network security, resists the malicious traffic attacks as much as possible, and ensuring the network security, the Gated Recurrent Unit (GRU) and Convolutional Neural Network (CNN) are combined. Then, a Software Defined Networking (SDN) anomaly detection architecture is built and continuously optimized to ensure network security as much as possible and enhance the reliability of the detection architecture. The results show that the proposed network architecture can greatly improve the accuracy of detection, and its performance will be different due to the different number of CNN layers. When the two-layer CNN structure is selected, its performance is the best among all algorithms. Especially, the accuracy of GRU- CNN-2 is 98.7%, which verifies that the proposed method is effective. Therefore, under deep learning, the utilization of GRU- CNN to explore and optimize the SDN anomaly detection is of great significance to ensure information transmission security in the future.

Industrial Control System (ICS) communication transmits monitoring and control data between industrial processes and the control station. ICS systems cover various domains of critical infrastructure such as the power plants, water and gas distribution, or aerospace traffic control. Security of ICS systems is usually implemented on the perimeter of the network using ICS enabled firewalls or Intrusion Detection Systems (IDSs). These techniques are helpful against external attacks, however, they are not able to effectively detect internal threats originating from a compromised device with malicious software. In order to mitigate or eliminate internal threats against the ICS system, we need to monitor ICS traffic and detect suspicious data transmissions that differ from common operational communication. In our research, we obtain ICS monitoring data using standardized IPFIX flows extended with meta data extracted from ICS protocol headers. Unlike other anomaly detection approaches, we focus on modelling the semantics of ICS communication obtained from the IPFIX flows that describes typical conversational patterns. This paper presents a technique for modelling ICS conversations using frequency prefix trees and Deterministic Probabilistic Automata (DPA). As demonstrated on the attack scenarios, these models are efficient to detect common cyber attacks like the command injection, packet manipulation, network scanning, or lost connection. An important advantage of our approach is that the proposed technique can be easily integrated into common security information and event management (SIEM) systems with Netflow/IPFIX support. Our experiments are performed on IEC 60870-5-104 (aka IEC 104) control communication that is widely used for the substation control in smart grids.

With the rapid advancement of the electrical grid, substation automation systems (SASs) have been developing continuously. However, with the introduction of advanced features, such as remote control, potential cyber security threats in SASs are also increased. Additionally, crucial components in SASs, such as protection relays, usually come from third-party vendors and may not be fully trusted. Untrusted devices may stealthily perform harmful or unauthorised behaviours which could compromise or damage SASs, and therefore, bring adverse impacts to the primary plant. Thus, it is necessary to detect abnormal behaviours from an untrusted device before it brings about catastrophic impacts. Anomaly detection techniques are suitable to detect anomalies in SASs as they only bring minimal side-effects to normal system operations. Many researchers have developed various machine learning algorithms and mathematical models to improve the accuracy of anomaly detection. However, without prudent feature selection, it is difficult to achieve high accuracy when detecting attacks launched from internal trusted networks, especially for stealthy message modification attacks which only modify message payloads slightly and imitate patterns of benign behaviours. Therefore, this paper presents choices of features which improve the accuracy of anomaly detection within SASs, especially for detecting “stealthy” attacks. By including two additional features, Boolean control data from message payloads and physical values from sensors, our method improved the accuracy of anomaly detection by decreasing the false-negative rate from 25% to 5% approximately.

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 concealment and confusion nature of insider threat makes it a challenging task for security analysts to identify insider threat from log data. To detect insider threat, we propose a novel gated recurrent unit (GRU) and multi-autoencoder based insider threat detection method, which is an unsupervised anomaly detection method. It takes advantage of the extremely unbalanced characteristic of insider threat data and constructs a normal behavior autoencoder with low reconfiguration error through multi-level filter behavior learning, and identifies the behavior data with high reconfiguration error as abnormal behavior. In order to achieve the high efficiency of calculation and detection, GRU and multi-head attention are introduced into the autoencoder. Use dataset v6.2 of the CERT insider threat as validation data and threat detection recall as evaluation metric. The experimental results show that the effect of the proposed method is obviously better than that of Isolation Forest, LSTM autoencoder and multi-channel autoencoders based insider threat detection methods, and it's an effective insider threat detection technology.

In recent years, insider threat incidents and losses of companies or organizations are on the rise, and internal network security is facing great challenges. Traditional intrusion detection methods cannot identify malicious behaviors of insiders. As an effective method, insider threat detection technology has been widely concerned and studied. In this paper, we use the tree structure method to analyze user behavior, form feature sequences, and combine the Copula Based Outlier Detection (COPOD) method to detect the difference between feature sequences and identify abnormal users. We experimented on the insider threat dataset CERT-IT and compared it with common methods such as Isolation Forest.

Internal attacks are one of the biggest cybersecurity issues to companies and businesses. Despite the implemented perimeter security systems, the risk of adversely affecting the security and privacy of the organization’s information remains very high. Actually, the detection of such a threat is known to be a very complicated problem, presenting many challenges to the research community. In this paper, we investigate the effectiveness and usefulness of using Autoencoder and Variational Autoencoder deep learning algorithms to automatically defend against insider threats, without human intervention. The performance evaluation of the proposed models is done on the public CERT dataset (CERT r4.2) that contains both benign and malicious activities generated from 1000 simulated users. The comparison results with other models show that the Variational Autoencoder neural network provides the best overall performance with a higher detection accuracy and a reasonable false positive rate.

Protecting Cyber-physical Systems (CPSs) is highly important for preserving sensitive information and detecting cyber threats. Developing a robust privacy-preserving anomaly detection method requires physical and network data about the systems, such as Supervisory Control and Data Acquisition (SCADA), for protecting original data and recognising cyber-attacks. In this paper, a new privacy-preserving anomaly detection framework, so-called PPAD-CPS, is proposed for protecting confidential information and discovering malicious observations in power systems and their network traffic. The framework involves two main modules. First, a data pre-processing module is suggested for filtering and transforming original data into a new format that achieves the target of privacy preservation. Second, an anomaly detection module is suggested using a Gaussian Mixture Model (GMM) and Kalman Filter (KF) for precisely estimating the posterior probabilities of legitimate and anomalous events. The performance of the PPAD-CPS framework is assessed using two public datasets, namely the Power System and UNSW-NB15 dataset. The experimental results show that the framework is more effective than four recent techniques for obtaining high privacy levels. Moreover, the framework outperforms seven peer anomaly detection techniques in terms of detection rate, false positive rate, and computational time.

Cloud computing is one of the greatest innovations and emerging technologies of the century. It incorporates networks, databases, operating systems, and virtualization technologies thereby bringing the security challenges associated with these technologies. Security Measures such as two-factor authentication, intrusion detection systems, and data backup are already in place to handle most of the security threats and vulnerabilities associated with these technologies but there are still other threats that may not be easily detected. Such a threat is a malicious user gaining access to the Virtual Machines (VMs) of other genuine users and using the Virtual Machine resources for their benefits without the knowledge of the user or the cloud service provider. This research proposes a model for proactive monitoring and detection of anomalies in VM resource usage. The proposed model can detect and pinpoint the time such anomaly occurred. Isolation Forest and One-Class Support Vector Machine (OCSVM) machine learning algorithms were used to train and test the model on sampled virtual machine workload trace using a combination of VM resource metrics together. OCSVM recorded an average F1-score of 0.97 and 0.89 for hourly and daily time series respectively while Isolation Forest has an average of 0.93 and 0.80 for hourly and daily time series. This result shows that both algorithms work for the model however OCSVM had a higher classification success rate than Isolation Forest.

Static information flow analysis (IFA) and dynamic information flow tracking (DIFT) have been widely employed in offline security analysis of computer programs. As security attacks become more sophisticated, there is a rising need for IFA and DIFT in production environment. However, existing systems usually deal with IFA and DIFT separately, and most DIFT systems incur significant performance overhead. We propose MIT to facilitate IFA and DIFT in online production environment. MIT offers mixed-mode information flow tracking at byte-granularity and incurs moderate runtime performance overhead. The core techniques consist of the extraction of taint semantics intermediate representation (TSIR) at compile-time and the decoupled execution of TSIR for information flow analysis. We conducted an extensive performance overhead evaluation on MIT to confirm its applicability in production environment. We also outline potential applications of MIT, including the implementation of data provenance checking and information flow based anomaly detection in real-world applications.

The pervasive and resource-constrained nature of Internet of Things (IoT) devices makes them attractive to be targeted by different means of cyber threats. There are a vast amount of botnets being deployed every day that aim to increase their presence on the Internet for realizing malicious activities with the help of the compromised interconnected devices. Therefore, monitoring IoT networks using intrusion detection systems is one of the major countermeasures against such threats. In this work, we present a machine learning based Wi-Fi intrusion detection system developed specifically for IoT devices. We show that a single multi-class classifier, which operates on the encrypted data collected from the wireless data link layer, is able to detect the benign traffic and six types of IoT attacks with an overall accuracy of 96.85%. Our model is a scalable one since there is no need to train different classifiers for different IoT devices. We also present an alternative attack classifier that outperforms the attack classification model which has been developed in an existing study using the same dataset.

The research proposal discloses a novel drone-based ad-hoc network that leverages acoustic information for power plant surveillance and utilizes a secure blockchain model for protecting the integrity of drone communication over the network. The paper presents a vision for the drone-based networks, wherein drones are employed for monitoring the complex power plant machinery. The drones record acoustic information generated by the power plants and detect anomalies or deviations in machine behavior based on collected acoustic data. The drones are linked to distributed network of computing devices in possession with the plant stakeholders, wherein each computing device maintains a chain of data blocks. The chain of data blocks represents one or more transactions associated with power plants, wherein transactions are related to high risk auditory data set accessed by the drones in an event of anomaly or machine failure. The computing devices add at least one data block to the chain of data blocks in response to valid transaction data, wherein the transaction data is validated by the computing devices owned by power plant personnel.

Industrial Control Systems (ICSs) are used in several domains such as Transportation, Manufacturing, Defense and Power Generation and Distribution. ICSs deal with complex physical systems in order to achieve an industrial purpose with operational safety. Security has not been taken into account by design in these systems that makes them vulnerable to cyberattacks.In this paper, we rely on existing public ICS datasets as well as on the existing literature of Machine Learning (ML) applications for anomaly detection in ICSs in order to improve detection scores. To perform this purpose, we propose a systematic framework, relying on established ML algorithms and suitable data preprocessing methods, which allows us to quickly get efficient, and surprisingly, better results than the literature. Finally, some recommendations for future public ICS dataset generations end this paper, which would be fruitful for improving future attack detection models and then protect new ICSs designed in the next future.

This paper describes the architecture and the fundamental methodology of an anomaly detector, which by continuously monitoring Simple Network Management Protocol data and by processing it as complex-events, is able to timely recognize patterns of faults and relevant cyber-attacks. This solution has been applied in the context of smart grids, and in particular as part of a security and resilience component of the Information and Communication Technologies (ICT) Gateway, a middleware-based architecture that correlates and fuses measurement data from different sources (e.g., Inverters, Smart Meters) to provide control coordination and to enable grid observability applications. The detector has been evaluated through experiments, where we selected some representative anomalies that can occur on the ICT side of the energy distribution infrastructure: non-malicious faults (indicated by patterns in the system resources usage), as well as effects of typical cyber-attacks directed to the smart grid infrastructure. The results show that the detection is promisingly fast and efficient.

Cyber security is an important concern in critical infrastructures such as banking and financial organizations, where a number of malicious insiders are involved. These insiders may be existing employees / users present within the organization and causing harm by performing any malicious activity and are commonly known as insider threats. Existing insider threat detection (ITD) methods are based on statistical analysis, machine and deep learning approaches. They monitor and detect malicious user activity based on pre-built rules which fails to detect unforeseen threats. Also, some of these methods require explicit feature engineering which results in high false positives. Apart from this, some methods choose relatively insufficient features and are computationally expensive which affects the classifier's accuracy. Hence, in this paper, a user behaviour based ITD method is presented to overcome the above limitations. It is a conceptually simple and flexible approach based on augmented decision making and anomaly detection. It consists of bi-directional long short term memory (bi-LSTM) for efficient feature extraction. For the purpose of classifying users as "normal" or "malicious", a binary class support vector machine (SVM) is used. CMU-CERT v4.2 dataset is used for testing the proposed method. The performance is evaluated using the following parameters: Accuracy, Precision, Recall, F- Score and AUC-ROC. Test results show that the proposed method outperforms the existing methods.

Modern cars are becoming more accessible targets for cyberattacks due to the proliferation of wireless communication channels. The intra-vehicle Controller Area Network (CAN) bus lacks authentication, which exposes critical components to interference from less secure, wirelessly compromised modules. To address this issue, we propose vProfile, a sender authentication system based on voltage fingerprints of Electronic Control Units (ECUs). vProfile exploits the physical properties of ECU output voltages on the CAN bus to determine the authenticity of bus messages, which enables the detection of both hijacked ECUs and external devices connected to the bus. We show the potential of vProfile using experiments on two production vehicles with precision and recall scores of over 99.99%. The improved identification rates and more straightforward design of vProfile make it an attractive improvement over existing methods.