Biblio

Moving target defense (MTD) is becoming popular with the advancements in Software Defined Networking (SDN) technologies. With centralized management through SDN, changing the network attributes such as routes to escape from attacks is simple and fast. Yet, the available alternate routes are bounded by the network topology, and a persistent attacker that continuously perform the reconnaissance can extract the whole link-map of the network. To address this issue, we propose to use virtual shadow networks (VSNs) by applying Network Function Virtualization (NFV) abilities to the network in order to deceive attacker with the fake topology information and not reveal the actual network topology and characteristics. We design this approach under a formal framework for Internet Service Provider (ISP) networks and apply it to the recently emerged indirect DDoS attacks, namely Crossfire, for evaluation. The results show that attacker spends more time to figure out the network behavior while the costs on the defender and network operations are negligible until reaching a certain network size.

Internet of Things (IoT) has an immense potential for a plethora of applications ranging from healthcare automation to defence networks and the power grid. The security of an IoT network is essentially paramount to the security of the underlying computing and communication infrastructure. However, due to constrained resources and limited computational capabilities, IoT networks are prone to various attacks. Thus, safeguarding the IoT network from adversarial attacks is of vital importance and can be realised through planning and deployment of effective security controls; one such control being an intrusion detection system. In this paper, we present a novel intrusion detection scheme for IoT networks that classifies traffic flow through the application of deep learning concepts. We adopt a newly published IoT dataset and generate generic features from the field information in packet level. We develop a feed-forward neural networks model for binary and multi-class classification including denial of service, distributed denial of service, reconnaissance and information theft attacks against IoT devices. Results obtained through the evaluation of the proposed scheme via the processed dataset illustrate a high classification accuracy.

Moving target defense (MTD) is a proactive defense mechanism of changing the attack surface to increase an attacker's confusion and/or uncertainty, which invalidates its intelligence gained through reconnaissance and/or network scanning attacks. In this work, we propose software-defined networking (SDN)-based MTD technique using the shuffling of IP addresses and port numbers aiming to obfuscate both network and transport layers' real identities of the host and the service for defending against the network reconnaissance and scanning attacks. We call our proposed MTD technique Random Host and Service Multiplexing, namely RHSM. RHSM allows each host to use random, multiple virtual IP addresses to be dynamically and periodically shuffled. In addition, it uses short-lived, multiple virtual port numbers for an active service running on the host. Our proposed RHSM is novel in that we employ multiplexing (or de-multiplexing) to dynamically change and remap from all the virtual IPs of the host to the real IP or the virtual ports of the services to the real port, respectively. Via extensive simulation experiments, we prove how effectively and efficiently RHSM outperforms a baseline counterpart (i.e., a static network without RHSM) in terms of the attack success probability and defense cost.

This paper work is focused on Performance comparison of intrusion detection system between DBN Algorithm and SPELM Algorithm. Researchers have used this new algorithm SPELM to perform experiments in the area of face recognition, pedestrian detection, and for network intrusion detection in the area of cyber security. The scholar used the proposed State Preserving Extreme Learning Machine(SPELM) algorithm as machine learning classifier and compared it's performance with Deep Belief Network (DBN) algorithm using NSL KDD dataset. The NSL- KDD dataset has four lakhs of data record; out of which 40% of data were used for training purposes and 60% data used in testing purpose while calculating the performance of both the algorithms. The experiment as performed by the scholar compared the Accuracy, Precision, recall and Computational Time of existing DBN algorithm with proposed SPELM Algorithm. The findings have show better performance of SPELM; when compared its accuracy of 93.20% as against 52.8% of DBN algorithm;69.492 Precision of SPELM as against 66.836 DBN and 90.8 seconds of Computational time taken by SPELM as against 102 seconds DBN Algorithm.

This paper presents the effects of problem based learning project on a high-school student in Technology school “Electronic systems” associated with Technical University Sofia. The problem is creating an intrusion detection system for Apache HTTP Server with duration 6 months. The intrusion detection system is based on a recurrent neural network classifier namely long-short term memory units.

Now a day, Wireless Sensor Networks are widely used in military applications by its applications, it is extended to healthcare, industrial environments and many more. As we know that, there are some unique features of WSNs such as limited power supply, minimum bandwidth and limited energy. So, to secure traditional network, multiple techniques are available, but we can't use same techniques to secure WSNs. So to increase the overall security of WSNs, we required new ideas as well as new approaches. In general, intrusion prevention is the primary issue in WSNs and intrusion detection already reached to saturation. Thus, we need an efficient solution for proactive intrusion prevention towards WSNs. Thus, formal validation of protocols in WSN is an essential area of research. This research paper aims to formally verify as well as model some protocol used for intrusion detection using AVISPA tool and HLPSL language. In this research paper, the results of authentication and DoS attacks were detected is presented, but there is a need to prevent such type of attacks. In this research paper, a system is proposed in order to avoid intrusion using machine learning for the wireless sensor network. So, the proposed system will be used for intrusion prevention in a wireless sensor network.

With wide application of networked control systems(N CSs), NCSs security have encountered severe challenges. In this paper, we propose a robust event-triggered controller design method under replay attacks, and the control signal on the plant is updated only when the event-triggering condition is satisfied. We develop a general random replay attack model rather than predetermined specific patterns for the occurrences of replay attacks, which allows to obtain random states to replay. We show that the proposed event-triggered control (ETC) scheme, if well designed, can tolerate some consecutive replay attacks, without affecting the corresponding closed-loop system stability and performance. A numerical examples is finally given to illustrate the effectiveness of our method.

The rapid development of the Cloud Computing Technologies (CCTs) has amended the conventional design of resource-constrained Network Control System (NCS) to the powerful and flexible design of Cloud-Based Networked Control System (CB-NCS) by relocating the processing part to the cloud server. This arrangement has produced many internets based exquisite applications. However, this new arrangement has also raised many network security challenges for the cloud-based control system related to cyber-physical part of the system. In the absence of robust verification methodology, an attacker can launch the modification attack in order to destabilize or take control of NCS. It is desirable that there shall be a solution authentication methodology used to verify whether the incoming solutions are coming from the cloud or not. This paper proposes a methodology used for the verification of the receiving solution to the local control system from the cloud using Karush-Kuhn-Tucker (KKT) conditions, which is then applied to actuator after verification and thus ensure the stability in case of modification attack.

Intrusion detection system (IDS) has become an essential layer in all the latest ICT system due to an urge towards cyber safety in the day-to-day world. Reasons including uncertainty in finding the types of attacks and increased the complexity of advanced cyber attacks, IDS calls for the need of integration of Deep Neural Networks (DNNs). In this paper, DNNs have been utilized to predict the attacks on Network Intrusion Detection System (N-IDS). A DNN with 0.1 rate of learning is applied and is run for 1000 number of epochs and KDDCup-`99' dataset has been used for training and benchmarking the network. For comparison purposes, the training is done on the same dataset with several other classical machine learning algorithms and DNN of layers ranging from 1 to 5. The results were compared and concluded that a DNN of 3 layers has superior performance over all the other classical machine learning algorithms.

Aiming at the problem of node identification in wireless networks, a method of node identification based on deep learning is proposed, which starts with the tiny features of nodes in radiofrequency layer. Firstly, in order to cut down the computational complexity, Principal Component Analysis is used to reduce the dimension of node sample data. Secondly, a convolution neural network containing two hidden layers is designed to extract local features of the preprocessed data. Stochastic gradient descent method is used to optimize the parameters, and the Softmax Model is used to determine the output label. Finally, the effectiveness of the method is verified by experiments on practical wireless ad-hoc network.

This paper analyzes information network security risk assessment methods and models. Firstly an improved AHP method is proposed to assign the value of assets for solving the problem of risk judgment matrix consistency effectively. And then the neural network technology is proposed to construct the neural network model corresponding to the risk judgment matrix for evaluating the individual risk of assets objectively, the methods for calculating the asset risk value and system risk value are given. Finally some application results are given. Practice proves that the methods are correct and effective, which has been used in information network security risk assessment application and offers a good foundation for the implementation of the automatic assessment.

Network situation value is an important index to measure network security. Establishing an effective network situation prediction model can prevent the occurrence of network security incidents, and plays an important role in network security protection. Through the understanding and analysis of the network security situation, we can see that there are many factors affecting the network security situation, and the relationship between these factors is complex., it is difficult to establish more accurate mathematical expressions to describe the network situation. Therefore, this paper uses the grey neural network as the prediction model, but because the convergence speed of the grey neural network is very fast, the network is easy to fall into local optimum, and the parameters can not be further modified, so the Multi-Swarm Chaotic Particle Optimization (MSCPO)is used to optimize the key parameters of the grey neural network. By establishing the nonlinear mapping relationship between the influencing factors and the network security situation, the network situation can be predicted and protected.

Security is one of the most important needs in network communication. Cryptography is a science which involves two techniques encryption and decryption and it basically enables to send sensitive and confidential data over the unsecure network. The basic idea of cryptography is concealing of the data from unauthenticated users as they can misuse the data. In this paper we use auto associative neural network concept of soft computing in combination with encryption technique to send data securely on communication network.

As we all know, computer network security evaluation is an important link in the field of network security. Traditional computer network security evaluation methods use BP neural network combined with network security standards to train and simulate. However, because BP neural network is easy to fall into local minimum point in the training process, the evalu-ation results are often inaccurate. In this paper, the LM (Levenberg-Marquard) algorithm is used to optimize the BP neural network. The LM-BP algorithm is constructed and applied to the computer network security evaluation. The results show that compared with the traditional evaluation algorithm, the optimized neural network has the advantages of fast running speed and accurate evaluation results.

Software has become an essential component of modern life, but when software vulnerabilities threaten the security of users, new ways of analyzing for software security must be explored. Using the National Institute of Standards and Technology's Juliet Java Suite, containing thousands of examples of defective Java methods for a variety of vulnerabilities, a prototype tool was developed implementing an array of Long-Short Term Memory Recurrent Neural Networks to detect vulnerabilities within source code. The tool employs various data preparation methods to be independent of coding style and to automate the process of extracting methods, labeling data, and partitioning the dataset. The result is a prototype command-line utility that generates an n-dimensional vulnerability prediction vector. The experimental evaluation using 44,495 test cases indicates that the tool can achieve an accuracy higher than 90% for 24 out of 29 different types of CWE vulnerabilities.

We present a unified communication architecture for security requirements in the industrial internet of things. Formulating security requirements in the language of OPC UA provides a unified method to communicate and compare security requirements within a heavily heterogeneous landscape of machines in the field. Our machine-readable data model provides a fully automatable approach for security requirement communication within the rapidly evolving fourth industrial revolution, which is characterized by high-grade interconnection of industrial infrastructures and self-configuring production systems. Capturing security requirements in an OPC UA compliant and unified data model for industrial control systems enables strong use cases within modern production plants and future supply chains. We implement our data model as well as an OPC UA server that operates on this model to show the feasibility of our approach. Further, we deploy and evaluate our framework within a reference project realized by 14 industrial partners and 7 research facilities within Germany.

Networked Control Systems (NCS) are widely used in Industry 4.0 to obtain better management and operational capabilities, as well as to reduce costs. However, despite the benefits provided by NCSs, the integration of communication networks with physical plants can also expose these systems to cyber threats. This work proposes a link monitoring strategy to identify linear time-invariant transfer functions performed by a Man-in-the-Middle during controlled data injection attacks in NCSs. The results demonstrate that the proposed identification scheme provides adequate accuracy when estimating the attack function, and does not interfere in the plant behavior when the system is not under attack.

This paper proposes a compensation control scheme against DoS attack for nonlinear cyber-physical systems (CPSs). The dynamical process of the nonlinear CPSs are described by T-S fuzzy model that regulated by the corresponding fuzzy rules. The communication link between the controller and the actuator under consideration may be unreliable, where Denialof-Service (DoS) attack is supposed to invade the communication link randomly. To compensate the negative effect caused by DoS attack, a compensation control scheme is designed to maintain the stability of the closed-loop system. With the aid of the Lyapunov function theory, a sufficient condition is established to ensure the stochastic stability and strict dissipativity of the closed-loop system. Finally, an iterative linearization algorithm is designed to determine the controller gain and the effectiveness of the proposed approach is evaluated through simulations.

In order to enhance the network security protection level of intelligent substation, this paper puts forward a model of intelligent substation network security defense system through the analysis of intelligent substation network security risk and protection demand, and using example proved the feasibility and effectiveness of the defense system. It is intelligent substation network security protection provides a new solution.

Flow-based network attack detection technology is able to identify many threats in network traffic. Existing techniques have several drawbacks: i) rule-based approaches are vulnerable because it needs all the signatures defined for the possible attacks, ii) anomaly-based approaches are not efficient because it is easy to find ways to launch attacks that bypass detection, and iii) both rule-based and anomaly-based approaches heavily rely on domain knowledge of networked system and cyber security. The major challenge to existing methods is to understand novel attack scenarios and design a model to detect novel and more serious attacks. In this paper, we investigate network attacks and unveil the key activities and the relationships between these activities. For that reason, we propose methods to understand the network security practices using theoretic concepts such as graph kernels. In addition, we integrate graph kernels over deep learning architecture to exploit the relationship expressiveness among network flows and combine ability of deep neural networks (DNNs) with deep architectures to learn hidden representations, based on the communication representation graph of each network flow in a specific time interval, then the flow-based network attack detection can be done effectively by measuring the similarity between the graphs to two flows. The proposed study provides the effectiveness to obtain insights about network attacks and detect network attacks. Using two real-world datasets which contain several new types of network attacks, we achieve significant improvements in accuracies over existing network attack detection tasks.

The H2020 European research project GHOST - Safe-Guarding Home IoT Environments with Personalised Real-time Risk Control - aims to deploy a highly effective security framework for IoT smart home residents through a novel reference architecture for user-centric cyber security in smart homes providing an unobtrusive and user-comprehensible solution. The aforementioned security framework leads to a transparent cyber security environment by increasing the effectiveness of the existing cyber security services and enhancing system's self-defence through disruptive software-enabled network security solutions. In this paper, GHOST security framework for IoT-based smart homes is presented. It is aiming to address the security challenges posed by several types of attacks, such as network, device and software. The effective design of the overall multi-layered architecture is analysed, with particular emphasis given to the integration aspects through dynamic and re-configurable solutions and the features provided by each one of the architectural layers. Additionally, real-life trials and the associated use cases are described showcasing the competences and potential of the proposed framework.

The borderless, dynamic, high dimensional and virtual natures of cyberspace have brought unprecedented hard situation for defenders. To fight uncertain challenges in versatile cyberspace, a security framework based on the cloud computing platform that facilitates containerization technology to create a security capability pool to generate and distribute security payload according to system needs. Composed by four subsystems of the security decision center, the image and container library, the decision rule base and the security event database, this framework distills structured knowledge from aggregated security events and then deliver security load to the managed network or terminal nodes directed by the decision center. By introducing such unified and standardized top-level security framework that is decomposable, combinable and configurable in a service-oriented manner, it could offer flexibility and effectiveness in reconstructing security resource allocation and usage to reach higher efficiency.

The defense-in-depth approach has been widely recommended for designing critical information infrastructure, however, the lack of holistic design guidelines makes it difficult for many organizations to adopt the concept. Therefore, this paper proposes a holistic architectural framework and guidelines based on ring-based nested network zones for designing such highly secured information systems. This novel security architectural framework and guidelines offer the overall structural design and implementation options for holistically designing the N-tier/shared nothing system architectures. The implementation options, e.g. for the zone's perimeters, are recommended to achieve different capability levels of security or to trade off among different required security attributes. This framework enables the adaptive capability suitable for different real-world contexts. This paper also proposes an attack-hops verification approach as a tool to evaluate the architectural design.

The concept of network slicing in 5G mobile networks introduces new challenges for security management: Given the combination of Infrastructure-as-a-Service cloud providers, mobile network operators as Software-as-a-Service providers, and the various verticals as customers, multi-layer and multi-tenancy-capable management architectures are required. This paper addresses the challenges for correlation of security events in such 5G scenarios with a focus on event processing at telecommunication service providers. After an analysis of the specific demand for network-slice-centric security event correlation in 5G networks, ongoing standardization efforts, and related research, we propose a multi-tenancy-capable event correlation architecture along with a scalable information model. The event processing, alerting, and correlation workflow is discussed and has been implemented in a network and security management system prototype, leading to a demonstration of first results acquired in a lab setup.

Although there has been notable progress in modeling cascading failures in power grids, few works included using machine learning algorithms. In this paper, cascading failures that lead to massive blackouts in power grids are predicted and classified into no, small, and large cascades using machine learning algorithms. Cascading-failure data is generated using a cascading failure simulator framework developed earlier. The data set includes the power grid operating parameters such as loading level, level of load shedding, the capacity of the failed lines, and the topological parameters such as edge betweenness centrality and the average shortest distance for numerous combinations of two transmission line failures as features. Then several machine learning algorithms are used to classify cascading failures. Further, linear regression is used to predict the number of failed transmission lines and the amount of load shedding during a cascade based on initial feature values. This data-driven technique can be used to generate cascading failure data set for any real-world power grids and hence, power-grid engineers can use this approach for cascade data generation and hence predicting vulnerabilities and enhancing robustness of the grid.