Francisco José Mora-Gimeno

Network Intrusion Detection System Embedded on a Smart Sensor

This paper proposes a Network Intrusion Detection System (NIDS) embedded in a smart-sensor-inspired device under a service-oriented architecture (SOA) approach which is able to operate independently as an anomaly-based NIDS, or integrated transparently in a Distributed Intrusion Detection System (DIDS). The proposal is innovative because it combines the advantages of the smart sensor approach and the subsequent offering of the NIDS functionality as a service with the SOA use to achieve their integration with other DIDS components. The main goal of this paper is to reduce the huge volume of management tasks inherent to this type of network services, as well as facilitating the design of DIDS whose managing complexity could be restricted within well-defined margins. This paper also addresses the construction of a physical sensor prototype. This prototype was used to carry out the tests that has demonstrated the proposals validity, providing detection and performance ratios similar to those of existing intrusion detection systems (IDS), but with the advantage of a zero-maintenance approach.

Industrial Machines as a Service: Modelling industrial machinery processes

In this paper is proposed a service model for the industrial machinery which provides a design pattern which details, classifies and organises the services that ideally the machine should possess in order to facilitate its self-management and proactive management of the business logic for which it is responsible. This pattern also establishes those services which will enable the machine to communicate and cooperate with other machines or manufacturing elements, as well as with the remaining business processes. The proposed pattern are based on service oriented architecture (SOA) and Web services extensions (WS-*) in order to ensure that the industrial machinery attains high levels of self management and especially so that it can show the rest of the organisation and from a perspective of functionality, in a normalised manner, overcoming barriers imposed by technological and physical restrictions typical of these components and which traditionally have kept them isolated from the general business model.

Normalization of Industrial Machinery with Embedded Devices and SOA

In the present paper we propose a method that permits visualization of manufacturing devices from a functional perspective. The aim of this method is to raise the abstraction level of manufacturing devices from the lower levels of production to the enterprise level of the business model. The target of this new approach is to integrate in a transparent way the resources, processes and, in general, the business logic of manufacturing levels using existing business models and achieving business continuity and process automation. The proposed method comprises two phases: the first phase that we have named industrial machinery normalization process; and the second phase that we have named manufacturing processes reorganization process. This paper focuses mainly on the former, i.e. specification of the hardware normalization and industrial machinery functionalities process.

Intrusion Detection Method Using Neural Networks Based on the Reduction of Characteristics

The application of techniques based on Artificial Intelligence for intrusion detection systems (IDS), mostly, artificial neural networks (ANN), is becoming a mainstream as well as an extremely effective approach to address some of the current problems in this area. Nevertheless, the selection criteria of the features to be used as inputs for the ANNs remains a problematic issue, which can be put, in a nutshell, as follows: The wider the detection spectrum of selected features is, the lower the performance efficiency of the process becomes and vice versa. This paper proposes sort of a compromise between both ends of the scale: a model based on Principal Component Analysis (PCA) as the chosen algorithm for reducing characteristics in order to maintain the efficiency without hindering the capacity of detection. PCA uses a data model to diminish the size of ANNs input vectors, ensuring a minimum loss of information, and consequently reducing the complexity of the neural classifier as well as maintaining stability in training times. A test scenario for validation purposes was developed, using based-on-ANN IDS. The results obtained based on the tests have demonstrated the validity of the proposal.

Wake on LAN Over the Internet as Web Service System on Chip

In this paper, we introduce a system on chip designed to run a particular Web service (WS) in an application-specific integrated circuit. The system has been designed devoid of processor and software and conceived as a hardware pattern for a trouble-free design of network services offered as WS in a service-oriented architecture (SOA). Therefore, the chip is not only able to act as a Simple Object Access Protocol service provider but also capable of registering the service on its own in an external broker server using the Universal Description, Discovery and Integration Standard publication protocol. This proposal has been named WS on chip, and its main goal is to implement more cost-effective and zero-management SOA network devices. To validate this approach, a prototypical device has been developed using a field-programmable gate array technology. The particular network service selected has been Wake on LAN (WoL) over the Internet, thus allowing any WS client to wake up any network node compatible with WoL technology. A full SOA scenario has also been developed to test the prototype functionalities and show the proposal validity.

Video and image processing with self-organizing neural networks

This paper aims to address the ability of self-organizing neural network models to manage video and image processing in real-time. The Growing Neural Gas networks (GNG) with its attributes of growth, flexibility, rapid adaptation, and excellent quality representation of the input space makes it a suitable model for real time applications. A number of applications are presented that includes: image compression, hand and medical image contours representation, surveillance systems, hand gesture recognition systems or 3D data reconstruction.

Security alert correlation using growing neural gas

The use of alert correlation methods in Distributed Intrusion Detection Systems (DIDS) has become an important process to address some of the current problems in this area. However, the efficiency obtained is far from optimal results. This paper presents a novel approach based on the integration of multiple correlation methods by using the neural network Growing Neural Gas (GNG). Moreover, since correlation systems have different detection capabilities, we have modified the learning algorithm to positively weight the best performing systems. The results show the validity of the proposal, both the multiple integration approach using GNG neural network and the weighting based on efficiency.

Building Visual Surveillance Systems with Neural Networks

Self-organising neural networks have shown promise in a variety of applications areas. Their massive and intrinsic parallelism makes those networks suitable to solve hard problems in image-analysis and computer vision applications, especially when non-stationary environments occur. Moreover, this kind of neural networks preserves the topology of an input space by using their inherited competitive learning property. In this work we use a kind of self-organising network, the Growing Neural Gas, to solve some computer vision tasks applied to visual surveillance systems. The neural network is also modified to accelerate the learning algorithm in order to support applications with temporal constraints. This feature has been used to build a system able to track image features in video sequences. The system automatically keeps the correspondence of features among frames in the sequence using its own structure. Information obtained during the tracking process and allocated in the neural network can also be used to analyse the objects motion.

A Secure Multi-Tier Mobile Edge Computing Model for Data Processing Offloading Based on Degree of Trust

Current mobile devices need to run applications with high computational demands and critical response times. The mobile edge computing (MEC) paradigm was developed to improve the performance of these devices. This new computation architecture allows for the mobile devices to execute applications on fog nodes at the network edge; this process is called data processing offloading. This article presents a security model for the externalization of application execution in multi-tier MEC environments. The principal novelty of this study is that the model is able to modify the required security level in each tier of the distributed architecture as a function of the degree of trust associated with that tier. The basic idea is that a higher degree of trust requires a lower level of security, and vice versa. A formal framework is introduced that represents the general environment of application execution in distributed MEC architectures. An architecture is proposed that allows for deployment of the model in production environments and is implemented for evaluation purposes. The results show that the security model can be applied in multi-tier MEC architectures and that the model produces a minimal overhead, especially for computationally intensive applications.