SCADA systems are widely used in critical infrastructure sectors, including electricity generation and distribution, oil and gas production and distribution, and water treatment and distribution. SCADA process control systems are typically isolated from the internet via firewalls. However, they may still be subject to illicit cyber penetrations and may be subject to cyber threats from disgruntled insiders. We have developed a set of command injection, data injection, and denial of service attacks which leverage the lack of authentication in many common control system communication protocols including MODBUS, DNP3, and EtherNET/IP. We used these exploits to aid in development of a neural network based intrusion detection system which monitors control system physical behavior to detect artifacts of command and response injection attacks. Finally, we present intrusion detection accuracy results for our neural network based IDS which includes input features derived from physical properties of the control system.

/pdf/on-scada-control-system-command-and-response-injection-and-4p1vq4wn3q.pdf

On SCADA control system command and response injection and intrusion detection

To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data.

/pdf/network-intrusion-detection-based-on-a-general-regression-80icw9k92t.pdf

Network intrusion detection based on a general regression neural network optimized by an improved artificial immune algorithm.

The Routh-Pade approximation problem relating to the construction of a stable reduced-order (rth-order) approximant Gr(s) for a given stable high-order (nth-order) transfer function G(s), so as to fully retain the first r time moments/Markov parameters of G(s) as well as to minimise the errors between a few subsequent time moments/Markov parameters of G(s) and those of Gr(s), is revisited. For the solution of this problem, a novel computer-aided method based on the well known Luus-Jaakola algorithm is proposed.

Obtaining Routh-Pade approximants using Luus-Jaakola algorithm

Routh Approximation is believed to witness tremendous usage in deriving the reduced models from their higher equivalents. Order reduction is a critical field of interest for researchers or control engineers dealing with practical and physical systems of higher order. Reason for the popularity of Routh Approximation among other reduction methodologies is its strength of computational simplicity, ease of access and the promise to retain the model stability. This paper accomplishes a survey of the available Routh Approximation algorithms in their varied configuration since five decades. Last survey report based on Routh Approximation was cited in late seventies as discussed in the paper. One prime reason for the outcome of this paper is the problem met by the authors during their own work for analysing varied configuration of Routh Approximation for order reduction. Many times, the arrangement, stated or performed, seemed to be already in existence. Thus, the paper would be helpful to the researchers...

Order Reduction Techniques via Routh Approximation: A Critical Survey

This paper deals with order reduction in discrete-time systems. The reduction technique is based on utilization of Routh approximation and multiplicative operator. Various combinations of Routh table are used to derive the desired numerator and denominator polynomial of reduced-order model. Numerical examples are presented to verify the proposed algorithm.

Order Reduction in z -Domain for Interval System Using an Arithmetic Operator

Intrusion Detection System is based on the belief that an intruder's behavior will be noticeably different from that of a legitimate user and would exploit security vulnerabilities. This paper proposes a neural network approach to improve the alert throughput of a network and making it attack prohibitive using IDS. For evolving and testing intrusion the KDD CUP 99 dataset are used. The result of proposed approach is found to be more efficient in the area of Intrusion Detection and promises a good scope for further research.

Neural network approach for intrusion detection

This paper presents a direct truncation methodology for reducing the order of large scale interval systems. The algorithm is computationally simple, and intuitively appealing. Numerical examples illustrating the effectiveness of the proposed method are included.

Direct truncation method for order reduction of discrete interval system

Analysis of higher-order interval system is an appealing topic of research demanding an appropriate methodology to reduce them to their lower approximate. This paper attempts to fulfill the requirement by introducing two different algorithms interlaced with the property of Mikhailov stability criterion. Precisely, the stated approach derives the reduced order denominator polynomial, and two separate techniques compute the numerator polynomials. Overall the two proposed algorithms are justified for their novelty through their implication over the numerical examples followed by their rational acceptability to a real-time test system.

Amit Kumar Choudhary

Papers

Neural network approach for intrusion detection

Order Reduction Techniques via Routh Approximation: A Critical Survey

Order Reduction in z -Domain for Interval System Using an Arithmetic Operator

Direct truncation method for order reduction of discrete interval system

Model order reduction of discrete-time interval system based on Mikhailov stability criterion