Deep Learning-based Anomaly Detection in Cyber-physical Systems

2021 ◽  
Vol 54 (5) ◽  
pp. 1-36
Author(s):  
Yuan Luo ◽  
Ya Xiao ◽  
Long Cheng ◽  
Guojun Peng ◽  
Danfeng (Daphne) Yao
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Cyber Physical Systems ◽  
Detection Methods ◽  
Future Research ◽  
Open Problems ◽  
Physical Systems ◽  
Domain Specific ◽  
Domain Specific Knowledge ◽  
Review State

Anomaly detection is crucial to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of CPSs and more sophisticated attacks, conventional anomaly detection methods, which face the growing volume of data and need domain-specific knowledge, cannot be directly applied to address these challenges. To this end, deep learning-based anomaly detection (DLAD) methods have been proposed. In this article, we review state-of-the-art DLAD methods in CPSs. We propose a taxonomy in terms of the type of anomalies, strategies, implementation, and evaluation metrics to understand the essential properties of current methods. Further, we utilize this taxonomy to identify and highlight new characteristics and designs in each CPS domain. Also, we discuss the limitations and open problems of these methods. Moreover, to give users insights into choosing proper DLAD methods in practice, we experimentally explore the characteristics of typical neural models, the workflow of DLAD methods, and the running performance of DL models. Finally, we discuss the deficiencies of DL approaches, our findings, and possible directions to improve DLAD methods and motivate future research.

Brief Survey on Attack Detection Methods for Cyber-Physical Systems

2020 ◽  
Vol 14 (4) ◽  
pp. 5329-5339 ◽  
Author(s):  
Sen Tan ◽  
Josep M. Guerrero ◽  
Peilin Xie ◽  
Renke Han ◽  
Juan C. Vasquez
Keyword(s):  
Cyber Physical Systems ◽  
Attack Detection ◽  
Detection Methods ◽  
Physical Systems

scholarly journals The Importance of Implementing Cyber Physical Systems to Acquire Real-Time Data and Indicators

J ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 147-153
Author(s):  
Paula Morella ◽  
María Pilar Lambán ◽  
Jesús Antonio Royo ◽  
Juan Carlos Sánchez
Keyword(s):  
Decision Making ◽  
Data Acquisition ◽  
Real Time ◽  
Failure Detection ◽  
Cyber Physical Systems ◽  
Future Research ◽  
Time Data ◽  
Physical Systems ◽  
The Real ◽  
Real Time Data

Among the new trends in technology that have emerged through the Industry 4.0, Cyber Physical Systems (CPS) and Internet of Things (IoT) are crucial for the real-time data acquisition. This data acquisition, together with its transformation in valuable information, are indispensable for the development of real-time indicators. Moreover, real-time indicators provide companies with a competitive advantage over the competition since they enhance the calculus and speed up the decision-making and failure detection. Our research highlights the advantages of real-time data acquisition for supply chains, developing indicators that would be impossible to achieve with traditional systems, improving the accuracy of the existing ones and enhancing the real-time decision-making. Moreover, it brings out the importance of integrating technologies 4.0 in industry, in this case, CPS and IoT, and establishes the main points for a future research agenda of this topic.

scholarly journals A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 517
Author(s):  
Seong-heum Kim ◽  
Youngbae Hwang
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Low Cost ◽  
Detection Methods ◽  
Future Research ◽  
3D Object ◽  
Practical Applications ◽  
Depth Sensors ◽  
Significant Research ◽  
3D Object Detection

Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints. This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection. For relatively low-cost data acquisition systems without depth sensors or cameras at multiple viewpoints, we first consider existing databases with 2D RGB photos and their relevant attributes. Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized. We present the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.

scholarly journals Embedded Deep Learning Prototyping Approach for Cyber-Physical Systems: Smart LIDAR Case Study

2021 ◽  
Vol 10 (1) ◽  
pp. 18
Author(s):  
Quentin Cabanes ◽  
Benaoumeur Senouci ◽  
Amar Ramdane-Cherif
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Computation Time ◽  
Physical World ◽  
Cyber Physical Systems ◽  
Physical Systems ◽  
Research Technology ◽  
Standard Design ◽  
Hardware Architectures ◽  
Voxel Grid

Cyber-Physical Systems (CPSs) are a mature research technology topic that deals with Artificial Intelligence (AI) and Embedded Systems (ES). They interact with the physical world via sensors/actuators to solve problems in several applications (robotics, transportation, health, etc.). These CPSs deal with data analysis, which need powerful algorithms combined with robust hardware architectures. On one hand, Deep Learning (DL) is proposed as the main solution algorithm. On the other hand, the standard design and prototyping methodologies for ES are not adapted to modern DL-based CPS. In this paper, we investigate AI design for CPS around embedded DL. The main contribution of this work is threefold: (1) We define an embedded DL methodology based on a Multi-CPU/FPGA platform. (2) We propose a new hardware design architecture of a Neural Network Processor (NNP) for DL algorithms. The computation time of a feed forward sequence is estimated to 23 ns for each parameter. (3) We validate the proposed methodology and the DL-based NNP using a smart LIDAR application use-case. The input of our NNP is a voxel grid hardware computed from 3D point cloud. Finally, the results show that our NNP is able to process Dense Neural Network (DNN) architecture without bias.

scholarly journals Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

2021 ◽  
Vol 11 (9) ◽  
pp. 4005
Author(s):  
Asep Maulana ◽  
Martin Atzmueller
Keyword(s):  
Anomaly Detection ◽  
Complex Networks ◽  
Pareto Front ◽  
Scoring Function ◽  
Cyber Physical Systems ◽  
Complex Interaction ◽  
Interaction Networks ◽  
Physical Systems ◽  
Human Interactions ◽  
Different Levels

Anomaly detection in complex networks is an important and challenging task in many application domains. Examples include analysis and sensemaking in human interactions, e.g., in (social) interaction networks, as well as the analysis of the behavior of complex technical and cyber-physical systems such as suspicious transactions/behavior in financial or routing networks; here, behavior and/or interactions typically also occur on different levels and layers. In this paper, we focus on detecting anomalies in such complex networks. In particular, we focus on multi-layer complex networks, where we consider the problem of finding sets of anomalous nodes for group anomaly detection. Our presented method is based on centrality-based many-objective optimization on multi-layer networks. Starting from the Pareto Front obtained via many-objective optimization, we rank anomaly candidates using the centrality information on all layers. This ranking is formalized via a scoring function, which estimates relative deviations of the node centralities, considering the density of the network and its respective layers. In a human-centered approach, anomalous sets of nodes can then be identified. A key feature of this approach is its interpretability and explainability, since we can directly assess anomalous nodes in the context of the network topology. We evaluate the proposed method using different datasets, including both synthetic as well as real-world network data. Our results demonstrate the efficacy of the presented approach.

Detecting Intrusions in Cyber-Physical Systems of Smart Cities

2019 ◽  
pp. 74-102 ◽  
Author(s):  
Ismail Butun ◽  
Patrik Österberg
Keyword(s):  
Anomaly Detection ◽  
Smart Cities ◽  
Cyber Physical Systems ◽  
Security And Privacy ◽  
Security Vulnerabilities ◽  
Physical Systems ◽  
Detection Systems ◽  
Comprehensive Survey ◽  
Privacy Violation ◽  
Detection Schemes

Interfacing the smart cities with cyber-physical systems (CPSs) improves cyber infrastructures while introducing security vulnerabilities that may lead to severe problems such as system failure, privacy violation, and/or issues related to data integrity if security and privacy are not addressed properly. In order for the CPSs of smart cities to be designed with proactive intelligence against such vulnerabilities, anomaly detection approaches need to be employed. This chapter will provide a brief overview of the security vulnerabilities in CPSs of smart cities. Following a thorough discussion on the applicability of conventional anomaly detection schemes in CPSs of smart cities, possible adoption of distributed anomaly detection systems by CPSs of smart cities will be discussed along with a comprehensive survey of the state of the art. The chapter will discuss challenges in tailoring appropriate anomaly detection schemes for CPSs of smart cities and provide insights into future directions for the researchers working in this field.

scholarly journals A Trustworthy Communication Hub for Cyber-Physical Systems

2019 ◽  
Vol 11 (10) ◽  
pp. 211
Author(s):  
Juhani Latvakoski ◽  
Jouni Heikkinen
Keyword(s):  
Service Providers ◽  
Cyber Physical Systems ◽  
Energy Resources ◽  
Distributed Energy Resources ◽  
Future Research ◽  
Distributed Energy ◽  
Physical Systems ◽  
Physical Resources ◽  
Efficient Resource ◽  
Related Service

The motivation for this research arises from the challenges in the trustworthy communications related operation of cyber-physical systems (CPS), especially in the energy and mobility domains. The increasing amount of distributed energy resources (DERs) of prosumers and electric vehicles requires new ways for CPS communications to enable information exchanges for smart operation in peak consumption hours and balancing power levels in the energy grids in order to lower the energy cost. The huge number of mobile appliances and the related service providers do not serve properly the privacy of the owners, owing to the vertical silo type of operating model in industries. As the results of this research, we provide a trustworthy communication hub for CPS (CPS hub) for solving the challenges related to trustworthy communications between physical resources owned by different stakeholders. The CPS hub realizes the communication spaces concept, and enables combined trust and communications processes when dynamic resources owned by different stakeholders are exchanging information. The evaluations showed that the provided CPS hub enable information exchanges between distributed energy resources of different stakeholders, so that they can join the aggregation process for more flexible and efficient resource usage in energy markets. The CPS hub enable interaction between heterogeneous physical devices of multiple stakeholders to exchange information so that, for example, authorities can see the situation in the emergency area and, simultaneously, the policies of the owners can be taken into concern. Despite limited evaluation scenarios, it is shown that consideration of the ownership issues in the trustworthy communication for information exchanges between heterogeneous physical resources (devices) is possible and feasible. Several future research items, such as, for example, scalability; real-time and streams based operation; as well as consideration of the security, privacy, trust, and safety challenges, were detected. However, the evaluations showed that the constructed CPS hub contribute a set of very essential technical enablers for future smart CPS systems and create strong a basis for such future research towards a future smart society.

Sign in / Sign up

Export Citation Format

Share Document