Biblio

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.

The paper considers the issue of recurrent neural networks applicability for detecting industrial process anomalies to detect intrusion in Industrial Control Systems. Cyberattack on Industrial Control Systems often leads to appearing of anomalies in industrial process. Thus, it is proposed to detect such anomalies by forecasting the state of an industrial process using a recurrent neural network and comparing the predicted state with actual process' state. In the course of experimental research, a recurrent neural network with one-dimensional convolutional layer was implemented. The Secure Water Treatment dataset was used to train model and assess its quality. The obtained results indicate the possibility of using the proposed method in practice. The proposed method is characterized by the absence of the need to use anomaly data for training. Also, the method has significant interpretability and allows to localize an anomaly by pointing to a sensor or actuator whose signal does not match the model's prediction.

We propose an autoencoder based approach to anomaly detection in smart grid systems. Data collecting sensors within smart home systems are susceptible to many data corruption issues, such as malicious attacks or physical malfunctions. By applying machine learning to a smart home or grid, sensor anomalies can be detected automatically for secure data collection and sensor-based system functionality. In addition, we tested the effectiveness of this approach on real smart home sensor data collected for multiple years. An early detection of such data corruption issues is essential to the security and functionality of the various sensors and devices within a smart home.

A non-predicted and transient malfunctioning of one or multiple unmanned aerial vehicles (UAVs) is something that may happen over a course of their deployment. Therefore, it is very important to have means to detect these events and take actions for ensuring a high level of reliability, security, and safety of the flight for the predefined mission. In this research, we propose algorithms aiming at the detection and isolation of any faulty UAV so that the performance of the UAVs application is kept at its highest level. To this end, we propose the use of Kullback-Leiler Divergence (KLD) and Artificial Neural Network (ANN) to build algorithms that detect and isolate any faulty UAV. The proposed methods are declined in these two directions: (1) we compute a difference between the internal and external data, use KLD to compute dissimilarities, and detect the UAV that transmits erroneous measurements. (2) Then, we identify the faulty UAV using an ANN model to classify the sensed data using the internal sensed data. The proposed approaches are validated using a real dataset, provided by the Air Lab Failure and Anomaly (ALFA) for UAV fault detection research, and show promising performance.

The use of modeling techniques such as Knuth's Rule or Bayesian Blocks for the purposes of real-time traffic characterization in RFID networks has been proposed already. This study examines the applicability of using Voronoi polygon maps or alternatively, DBSCAN clustering, as initial density estimation techniques when computing 2-Dimentional Bayesian Blocks models of RFID traffic. Our results are useful for the purposes of extending the constant-piecewise adaptation of Bayesian Blocks into 2D piecewise models for the purposes of more precise detection of anomalies in RFID traffic based on multiple log features such as command type, location, UID values, security support, etc. Automatic anomaly detection of RFID networks is an essential first step in the implementation of intrusion detection as well as a timely response to equipment malfunction such as tag hardware failure.

The following topics are dealt with: security of data; distributed power generation; power engineering computing; power grids; power system security; computer network security; voltage control; risk management; power system measurement; critical infrastructures.

With current IoT architectures, once a single device in a network is compromised, it can be used to disrupt the behavior of other devices on the same network. Even though system administrators can secure critical devices in the network using best practices and state-of-the-art technology, a single vulnerable device can undermine the security of the entire network. The goal of this work is to limit the ability of an attacker to exploit a vulnerable device on an IoT network and fabricate deceitful messages to co-opt other devices. The approach is to limit attackers by using device proxies that are used to retransmit and control network communications. We present an architecture that prevents deceitful messages generated by compromised devices from affecting the rest of the network. The design assumes a centralized and trustworthy machine that can observe the behavior of all devices on the network. The central machine collects application layer data, as opposed to low-level network traffic, from each IoT device. The collected data is used to train models that capture the normal behavior of each individual IoT device. The normal behavioral data is then used to monitor the IoT devices and detect anomalous behavior. This paper reports on our experiments using both a binary classifier and a density-based clustering algorithm to model benign IoT device behavior with a realistic test-bed, designed to capture normal behavior in an IoT-monitored environment. Results from the IoT testbed show that both the classifier and the clustering algorithms are promising and encourage the use of application-level data for detecting compromised IoT devices.

Recent advancements in the field of in-vehicle network and wireless communication, has been steadily progressing. Also, the advent of technologies such as Vehicular Adhoc Networks (VANET) and Intelligent Transportation System (ITS), has transformed modern automobiles into a sophisticated cyber-physical system rather than just a isolated mechanical device. Modern automobiles rely on many electronic control units communicating over the Controller Area Network (CAN) bus. Although protecting the car's external interfaces is an vital part of preventing attacks, detecting malicious activity on the CAN bus is an effective second line of defense against attacks. This paper proposes a hybrid anomaly detection system for CAN bus based on patterns of recurring messages and time interval of messages. The proposed method does not require modifications in CAN bus. The proposed system is evaluated on real CAN bus traffic with simulated attack scenarios. Results obtained show that our proposed system achieved a good detection rate with fast response times.

Science DMZs are specialized networks that enable large-scale distributed scientific research, providing efficient and guaranteed performance while transferring large amounts of data at high rates. The high-speed performance of a Science DMZ is made viable via data transfer nodes (DTNs), therefore they are a critical point of failure. DTNs are usually monitored with network intrusion detection systems (NIDS). However, NIDS do not consider system performance data, such as network I/O interrupts and context switches, which can also be useful in revealing anomalous system performance potentially arising due to external network based attacks or insider attacks. In this paper, we demonstrate how system performance metrics can be applied towards securing a DTN in a Science DMZ network. Specifically, we evaluate the effectiveness of system performance data in detecting TCP-SYN flood attacks on a DTN using DBSCAN (a density-based clustering algorithm) for anomaly detection. Our results demonstrate that system interrupts and context switches can be used to successfully detect TCP-SYN floods, suggesting that system performance data could be effective in detecting a variety of attacks not easily detected through network monitoring alone.

Application programs are a possible source of attacks to databases as attackers might exploit vulnerabilities in a privileged database application. They can perform code injection or code-reuse attack in order to steal sensitive data. However, as such attacks very often result in changes in the program's behavior, program monitoring techniques represent an effective defense to detect on-going attacks. One such technique is monitoring the library/system calls that the application program issues while running. In this paper, we propose AD-PROM, an Anomaly Detection system that aims at protecting relational database systems against malicious/compromised applications PROgraMs aiming at stealing data. AD-PROM tracks calls executed by application programs on data extracted from a database. The system operates in two phases. The first phase statically and dynamically analyzes the behavior of the application in order to build profiles representing the application's normal behavior. AD-PROM analyzes the control and data flow of the application program (i.e., static analysis), and builds a hidden Markov model trained by the program traces (i.e., dynamic analysis). During the second phase, the program execution is monitored in order to detect anomalies that may represent data leakage attempts. We have implemented AD-PROM and carried experimental activities to assess its performance. The results showed that our system is highly accurate in detecting changes in the application programs' behaviors and has very low false positive rates.

The following topics are dealt with: authorisation; data privacy; mobile computing; security of data; cryptography; Internet of Things; message authentication; invasive software; Android (operating system); vectors.

Much research is concentrated on improving models for host-based intrusion detection systems (HIDS). Typically, such research aims at improving a model's results (e.g., reducing the false positive rate) in the familiar static training/testing environment using the standard data sources. Matching advancements in the machine learning community, researchers in the syscall HIDS domain have developed many complex and powerful syscall-based models to serve as anomaly detectors. These models typically show an impressive level of accuracy while emphasizing on minimizing the false positive rate. However, with each proposed model iteration, we get further from the setting in which these models are intended to operate. As kernels become more ornate and hardened, the implementation space for anomaly detection models is narrowing. Furthermore, the rapid advancement of operating systems and the underlying complexity introduced dictate that the sometimes decades-old datasets have long been obsolete. In this paper, we attempt to bridge the gap between theoretical models and their intended application environments by examining the recent Linux kernel 5.7.0-rc1. In this setting, we examine the feasibility of syscall-based HIDS in modern operating systems and the constraints imposed on the HIDS developer. We discuss how recent advancements to the kernel have eliminated the previous syscall trace collect method of writing syscall table wrappers, and propose a new approach to generate data and place our detection model. Furthermore, we present the specific execution time and memory constraints that models must meet in order to be operable within their intended settings. Finally, we conclude with preliminary results from our model, which primarily show that in-kernel machine learning models are feasible, depending on their complexity.

MIL-STD-1553 is a military standard that defines the specification of a serial communication bus that has been implemented in military and aerospace avionic platforms for over 40 years. MIL-STD-1553 was designed for a high level of fault tolerance while less attention was paid to cyber security issues. Thus, as indicated in recent studies, it is exposed to various threats. In this article, we suggest enhancing the security of MIL-STD-1553 communication buses by integrating a machine learning-based intrusion detection system (IDS); such anIDS will be capable of detecting cyber attacks in real time. The IDS consists of two modules: 1) a remote terminal (RT) authentication module that detects illegitimately connected components and data transfers and 2) a sequence-based anomaly detection module that detects anomalies in the operation of the system. The IDS showed high detection rates for both normal and abnormal behavior when evaluated in a testbed using real 1553 hardware, as well as a very fast and accurate training process using logs from a real system. The RT authentication module managed to authenticate RTs with +0.99 precision and +0.98 recall; and detect illegitimate component (or a legitimate component that impersonates other components) with +0.98 precision and +0.99 recall. The sequence-based anomaly detection module managed to perfectly detect both normal and abnormal behavior. Moreover, the sequencebased anomaly detection module managed to accurately (i.e., zero false positives) model the normal behavior of a real system in a short period of time ( 22 s).

Anomaly detection (AD) is very important across several real-world problems in the heavy industries and Internet-of-Things (IoT) domains. Traditional methods so far have categorized anomaly detection into (a) unsupervised, (b) semi-supervised and (c) supervised techniques. A relatively unexplored direction is the development of context aware anomaly detection systems which can build on top of any of these three techniques by using side information. Context can be captured from a different modality such as semantic graphs encoding grouping of sensors governed by the physics of the asset. Process flow diagrams of an operational plant depicting causal relationships between sensors can also provide useful context for ML algorithms. Capturing such semantics by itself can be pretty challenging, however, our paper mainly focuses on, (a) designing and implementing effective anomaly detection pipelines using sparse Gaussian Graphical Models with various statistical distance metrics, and (b) differentiating these pipelines by embedding contextual semantics inferred from graphs so as to obtain better KPIs in practice. The motivation for the latter of these two has been explained above, and the former in particular is well motivated by the relatively mediocre performance of highly parametric deep learning methods for small tabular datasets (compared to images) such as IoT sensor data. In contrast to such traditional automated deep learning (AutoAI) techniques, our anomaly detection system is based on developing semantics-driven industry specific ML pipelines which perform scalable computation evaluating several models to identify the best model. We benchmark our AD method against state-of-the-art AD techniques on publicly available UCI datasets. We also conduct a case study on IoT sensor and semantic data procured from a large thermal energy asset to evaluate the importance of semantics in enhancing our pipelines. In addition, we also provide explainable insights for our model which provide a complete perspective to a reliability engineer.

Legacy and novel network services are expected to be migrated and designed to be deployed in fully virtualized environments. Starting with 5G, NFV becomes a formally required brick in the specifications, for services integrated within the infrastructure provider networks. This evolution leads to deployment of virtual resources Virtual-Machine (VM)-based, container-based and/or server-less platforms, all calling for a deep virtualization of infrastructure components. Such a network softwarization also unleashes further logical network virtualization, easing multi-layered, multi-actor and multi-access services, so as to be able to fulfill high availability, security, privacy and resilience requirements. However, the derived increased components heterogeneity makes the detection and the characterization of anomalies difficult, hence the relationship between anomaly detection and corresponding reconfiguration of the NFV stack to mitigate anomalies. In this article we propose an unsupervised machine-learning data-driven approach based on Long-Short- Term-Memory (LSTM) autoencoders to detect and characterize anomalies in virtualized networking services. With a radiography visualization, this approach can spot and describe deviations from nominal parameter values of any virtualized network service by means of a lightweight and iterative mean-squared reconstruction error analysis of LSTM-based autoencoders. We implement and validate the proposed methodology through experimental tests on a vIMS proof-of-concept deployed using Kubernetes.

The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system. However, manipulated power flow measurements can potentially hide overloads and bypass the bad data detection scheme to interfere the validity of estimated states. In this paper, we use an autoencoder neural network to detect anomalous system states and investigate the impact of hyperparameters on the detection performance for false data injection attacks that target power flows. Experimental results on the IEEE 118 bus system indicate that the proposed mechanism has the ability to achieve satisfactory learning efficiency and detection accuracy.

The complexity and ubiquity of modern computing systems is a fertile ground for anomalies, including security and privacy breaches. In this paper, we propose a new methodology that addresses the practical challenges to implement anomaly detection approaches. Specifically, it is challenging to define normal behavior comprehensively and to acquire data on anomalies in diverse cloud environments. To tackle those challenges, we focus on anomaly detection approaches based on system performance signatures. In particular, performance signatures have the potential of detecting zero-day attacks, as those approaches are based on detecting performance deviations and do not require detailed knowledge of attack history. The proposed methodology leverages an analytical performance model and experimentation, and allows to control the rate of false positives in a principled manner. The methodology is evaluated using the TPCx-V workload, which was profiled during a set of executions using resource exhaustion anomalies that emulate the effects of anomalies affecting system performance. The proposed approach was able to successfully detect the anomalies, with a low number of false positives (precision 90%-98%).

State estimation is of considerable significance for the power system operation and control. However, well-designed false data injection attacks can utilize blind spots in conventional residual-based bad data detection methods to manipulate measurements in a coordinated manner and thus affect the secure operation and economic dispatch of grids. In this paper, we propose a detection approach based on an autoencoder neural network. By training the network on the dependencies intrinsic in `normal' operation data, it effectively overcomes the challenge of unbalanced training data that is inherent in power system attack detection. To evaluate the detection performance of the proposed mechanism, we conduct a series of experiments on the IEEE 118-bus power system. The experiments demonstrate that the proposed autoencoder detector displays robust detection performance under a variety of attack scenarios.

Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed scenario. These deep learning methods use large-scale training data with large complexity. As a solution, in this paper, we show how to use pre-trained convolutional neural net models to perform feature extraction and context mining, and then use denoising autoencoder with relatively low model complexity to provide efficient and accurate surveillance anomaly detection, which can be useful for the resource-constrained devices such as edge devices of the Internet of Things (IoT). Our anomaly detection model makes decisions based on the high-level features derived from the selected embedded computer vision models such as object classification and object detection. Additionally, we derive contextual properties from the high-level features to further improve the performance of our video anomaly detection method. We use two UCSD datasets to demonstrate that our approach with relatively low model complexity can achieve comparable performance compared to the state-of-the-art approaches.

Statistical structure learning (SSL)-based approaches have been employed in the recent years to detect different types of anomalies in a variety of cyber-physical systems (CPS). Although these approaches outperform conventional methods in the literature, their computational complexity, need for large number of measurements and centralized computations have limited their applicability to large-scale networks. In this work, we propose a distributed, multi-agent maximum likelihood (ML) approach to detect anomalies in smart grid applications aiming at reducing computational complexity, as well as preserving data privacy among different players in the network. The proposed multi-agent detector breaks the original ML problem into several local (smaller) ML optimization problems coupled by the alternating direction method of multipliers (ADMM). Then, these local ML problems are solved by their corresponding agents, eventually resulting in the construction of the global solution (network's information matrix). The numerical results obtained from two IEEE test (power transmission) systems confirm the accuracy and efficiency of the proposed approach for anomaly detection.

In January 2017 encrypted Internet traffic surpassed non-encrypted traffic. Although encryption increases security, it also masks intrusions and attacks by blocking the access to packet contents and traffic features, therefore making data analysis unfeasible. In spite of the strong effect of encryption, its impact has been scarcely investigated in the field. In this paper we study how encryption affects flow feature spaces and machine learning-based attack detection. We propose a new cross-layer feature vector that simultaneously represents traffic at three different levels: application, conversation, and endpoint behavior. We analyze its behavior under TLS and IPSec encryption and evaluate the efficacy with recent network traffic datasets and by using Random Forests classifiers. The cross-layer multi-key approach shows excellent attack detection in spite of TLS encryption. When IPsec is applied, the reduced variant obtains satisfactory detection for botnets, yet considerable performance drops for other types of attacks. The high complexity of network traffic is unfeasible for monolithic data analysis solutions, therefore requiring cross-layer analysis for which the multi-key vector becomes a powerful profiling core.

As we notice the increasing adoption of Cellular IoT solutions (smart-home, e-health, among others), there are still some security aspects that can be improved as these devices can suffer various types of attacks that can have a high-impact over our daily lives. In order to avoid this, we present a multi-front security solution that consists on a federated cross-layered authentication mechanism, as well as a machine learning platform with anomaly detection techniques for data traffic analysis as a way to study devices' behavior so it can preemptively detect attacks and minimize their impact. In this paper, we also present a proof-of-concept to illustrate the proposed solution and showcase its feasibility, as well as the discussion of future iterations that will occur for this work.

In this paper, we assess the vulnerability of network anomaly detection systems that use machine learning methods. Although the performance of these network anomaly detection systems is high in comparison to that of existing methods without machine learning methods, the use of machine learning methods for detecting vulnerabilities is a growing concern among researchers of image processing. If the vulnerabilities of machine learning used in the network anomaly detection method are exploited by attackers, large security threats are likely to emerge in the near future. Therefore, in this paper we clarify how vulnerability detection of machine learning network anomaly detection methods affects their performance.

Anomaly detection classification technology based on deep learning is one of the crucial technologies supporting network security. However, as the data increasing, this traditional model cannot guarantee that the false alarm rate is minimized while meeting the high detection rate. Additionally, distribution of imbalanced abnormal samples will lead to an increase in the error rate of the classification results. In this work, since CNN is effective in network intrusion classification, we embed a compressed feature layer in CNN (Convolutional Neural Networks). The purpose is to improve the efficiency of network intrusion detection. After our model was trained for 55 epochs and we set the learning rate of the model to 0.01, the detection rate reaches over 98%.

The key feature of NDN is in-network caching that every router has its cache to store data for future use, thus improve the usage of the network bandwidth and reduce the network latency. However, in-network caching increases the security risks - cache pollution attacks (CPA), which includes locality disruption (ruining the cache locality by sending random requests for unpopular contents to make them popular) and False Locality (introducing unpopular contents in the router's cache by sending requests for a set of unpopular contents). In this paper, we propose a machine learning method, named Triangle Area Based Multivariate Correlation Analysis (TAB-MCA) that detects the cache pollution attacks in NDN. This detection system has two parts, the triangle-area-based MCA technique, and the threshold-based anomaly detection technique. The TAB-MCA technique is used to extract hidden geometrical correlations between two distinct features for all possible permutations and the threshold-based anomaly detection technique. This technique helps our model to be able to distinguish attacks from legitimate traffic records without requiring prior knowledge. Our technique detects locality disruption, false locality, and combination of the two with high accuracy. Implementation of XC-topology, the proposed method shows high efficiency in mitigating these attacks. In comparison to other ML-methods, our proposed method has a low overhead cost in mitigating CPA as it doesn't require attackers' prior knowledge. Additionally, our method can also detect non-uniform attack distributions.