scholarly journals Algorithm Design for Resilient Cyber-Physical Systems using an Automated Attack Generative Model

2021 ◽  
Author(s):  
Yu Zheng ◽  
Ali Sayghe ◽  
Olugbenga Anubi
Keyword(s):  
High Performance ◽  
Water Distribution ◽  
Algorithm Design ◽  
Cyber Physical Systems ◽  
Generative Model ◽  
Training Data ◽  
Pruning Algorithm ◽  
Physical Systems ◽  
Injection Attacks ◽  
Localization Algorithms

<div>This paper presents a suite of algorithms for detecting and localizing attacks in cyber-physical systems, and performing improved resilient state estimation through a pruning algorithm. High performance rates for the underlying detection and localization algorithms are achieved by generating training data that cover large region of the attack space. An unsupervised generative model trained by physics-based discriminators is designed to generate successful false data injection attacks. Then the generated adversarial examples are used to train a multi-class deep neural network which detects and localizes the attacks on measurements. Next, a pruning algorithm is included to improve the precision of localization result and provide performance guarantees for the resulting resilient observer. The performance of the proposed method is validated using the numerical simulation of a water distribution cyber-physical system.</div>

scholarly journals Algorithm Design for Resilient Cyber-Physical Systems using an Automated Attack Generative Model

2021 ◽  
Author(s):  
Yu Zheng ◽  
Ali Sayghe ◽  
Olugbenga Anubi
Keyword(s):  
High Performance ◽  
Water Distribution ◽  
Algorithm Design ◽  
Cyber Physical Systems ◽  
Generative Model ◽  
Training Data ◽  
Pruning Algorithm ◽  
Physical Systems ◽  
Injection Attacks ◽  
Localization Algorithms

<div>This paper presents a suite of algorithms for detecting and localizing attacks in cyber-physical systems, and performing improved resilient state estimation through a pruning algorithm. High performance rates for the underlying detection and localization algorithms are achieved by generating training data that cover large region of the attack space. An unsupervised generative model trained by physics-based discriminators is designed to generate successful false data injection attacks. Then the generated adversarial examples are used to train a multi-class deep neural network which detects and localizes the attacks on measurements. Next, a pruning algorithm is included to improve the precision of localization result and provide performance guarantees for the resulting resilient observer. The performance of the proposed method is validated using the numerical simulation of a water distribution cyber-physical system.</div>

scholarly journals Leveraging Stack4Things for Federated Learning in Intelligent Cyber Physical Systems

2020 ◽  
Vol 9 (4) ◽  
pp. 59
Author(s):  
Fabrizio De Vita ◽  
Dario Bruneo
Keyword(s):  
Intelligent Systems ◽  
Physical World ◽  
Cyber Physical Systems ◽  
Training Data ◽  
Cloud Platform ◽  
Model Accuracy ◽  
Training Time ◽  
Physical Systems ◽  
The Internet Of Things ◽  
And Training

During the last decade, the Internet of Things acted as catalyst for the big data phenomenon. As result, modern edge devices can access a huge amount of data that can be exploited to build useful services. In such a context, artificial intelligence has a key role to develop intelligent systems (e.g., intelligent cyber physical systems) that create a connecting bridge with the physical world. However, as time goes by, machine and deep learning applications are becoming more complex, requiring increasing amounts of data and training time, which makes the use of centralized approaches unsuitable. Federated learning is an emerging paradigm which enables the cooperation of edge devices to learn a shared model (while keeping private their training data), thereby abating the training time. Although federated learning is a promising technique, its implementation is difficult and brings a lot of challenges. In this paper, we present an extension of Stack4Things, a cloud platform developed in our department; leveraging its functionalities, we enabled the deployment of federated learning on edge devices without caring their heterogeneity. Experimental results show a comparison with a centralized approach and demonstrate the effectiveness of the proposed approach in terms of both training time and model accuracy.

RISKNOUGHT: Stress-testing platform for cyber-physical water distribution networks

2020 ◽  
Author(s):  
Dionysios Nikolopoulos ◽  
Georgios Moraitis ◽  
Dimitrios Bouziotas ◽  
Archontia Lykou ◽  
George Karavokiros ◽  
...  
Keyword(s):  
Water Distribution ◽  
Stress Testing ◽  
Distribution Networks ◽  
Cyber Physical Systems ◽  
Water Utilities ◽  
Water Distribution Networks ◽  
Control Logic ◽  
Physical Systems ◽  
Testing Platform ◽  
The Impact

&lt;p&gt;Emergent threats in the water sector have the form of cyber-physical attacks that target SCADA systems of water utilities. Examples of attacks include chemical/biological contamination, disruption of communications between network elements and manipulating sensor data. RISKNOUGHT is an innovative cyber-physical stress testing platform, capable of modelling water distribution networks as cyber-physical systems. The platform simulates information flow of the cyber layer&amp;#8217;s networking and computational elements and the feedback interactions with the physical processes under control. RISKNOUGHT utilizes an EPANET-based solver with pressure-driven analysis functionality for the physical process and a customizable network model for the SCADA system representation, which is capable of implementing complex control logic schemes within a simulation. The platform enables the development of composite cyber-physical attacks on various elements of the SCADA including sensors, actuators and PLCs, assessing the impact they have on the hydraulic response of the distribution network, the quality of supplied water and the level of service to consumers. It is envisaged that this platform could help water utilities navigate the ever-changing risk landscape of the digital era and help address some of the modern challenges due to the ongoing transformation of water infrastructure into cyber-physical systems.&lt;/p&gt;

FPGA on Cyber-Physical Systems for the Implementation of Internet of Things

2020 ◽  
pp. 82-96
Author(s):  
Rajit Nair ◽  
Preeti Nair ◽  
Vidya Kant Dwivedi
Keyword(s):  
High Performance ◽  
Management Strategies ◽  
Cyber Physical Systems ◽  
Edge Computing ◽  
Reconfigurable Systems ◽  
Smart Power ◽  
Physical Systems ◽  
Computing Performance ◽  
High Level ◽  
Processing Architecture

Today, in cyber-physical systems, there is a transformation in which processing has been done on distributed mode rather than performing on centralized manner. Usually this type of approach is known as Edge computing, which demands hardware time to time when requirements in computing performance get increased. Considering this situation, we must remain energy efficient and adaptable. So, to meet the above requirements, SRAM-based FPGAs and their inherent run-time reconfigurability are integrated with smart power management strategies. Sometimes this approach fails in the case of user accessibility and easy development. This chapter presents an integrated framework to develop FPGA-based high-performance embedded systems for Edge computing in cyber-physical systems. The processing architecture will be based on hardware that helps us to manage reconfigurable systems from high level systems without any human intervention.

Sign in / Sign up

Export Citation Format

Share Document