Biblio

Many critical industrial control systems integrate a mixture of state-of-the-art and legacy equipment. Legacy installations lack advanced, and often even basic security features, risking entire system security. Existing research primarily focuses on the development of secure protocols for emerging devices or protocol translation proxies for legacy equipment. However, a robust security framework not only needs encryption but also mechanisms to prevent reconnaissance and unauthorized access to industrial devices. This paper proposes a novel Edge Security Gateway (ESG) that provides both, communication and endpoint security. The ESG is based on double ratchet algorithm and encrypts every message with a different key. It manages the ongoing renewal of short-lived session keys and provides localized firewall protection to individual devices. The ESG is easily customizable for a wide range of industrial application. As a use case, this paper presents the design and validation for synchrophasor technology in smart grid. The ESG effectiveness is practically validated in detecting reconnaissance, manipulation, replay, and command injection attacks due to its perfect forward and backward secrecy properties.

To ensure a ship’s fully operational status in a wide spectrum of missions, as passenger transportation, international trade, and military activities, numerous interdependent systems are essential. Despite the potential critical consequences of misunderstanding or ignoring those interdependencies, there are very few documented approaches to enable their identification, representation, analysis, and use. From the cybersecurity point of view, if an anomaly occurs on one of the interdependent systems, it could eventually impact the whole ship, jeopardizing its mission success. This paper presents a proposal to identify the main dependencies of layers within and between generic ship’s functional blocks. An analysis of one of these layers, the platform systems, is developed to examine a naval cyber-physical system (CPS), the water management for passenger use, and its associated dependencies, from an intrinsic perspective. This analysis generates a three layers graph, on which dependencies are represented as oriented edges. Each abstraction level of the graph represents the physical, digital, and system variables of the examined CPS. The obtained result confirms the interest of graphs for dependencies representation and analysis. It is an operational depiction of the different systems interdependencies, on which can rely a cybersecurity evaluation, like anomaly detection and propagation assessment.

Naval vessels infrastructures are evolving towards increasingly connected and automatic systems. Such accelerated complexity boost to search for more adapted and useful navigation devices may be at odds with cybersecurity, making necessary to develop adapted analysis solutions for experts. This paper introduces a novel process to visualize and analyze naval Cyber-Physical Systems (CPS) using oriented graphs, considering operational constraints, to represent physical and functional connections between multiple components of CPS. Rapid prototyping of interconnected components is implemented in a semi-automatic manner by defining the CPS’s digital and physical systems as nodes, along with system variables as edges, to form three layers of an oriented graph, using the open-source Neo4j software suit. The generated multi-layer graph can be used to support cybersecurity analysis, like attacks simulation, anomaly detection and propagation estimation, applying existing or new algorithms.

The subgraph matching problem arises in a number of modern machine learning applications including segmented images and meshes of 3D objects for pattern recognition, bio-chemical reactions and security applications. This graph-based problem can have a very large and complex solution space especially when the world graph has many more nodes and edges than the template. In a real use-case scenario, analysts may need to query additional information about template nodes or world nodes to reduce the problem size and the solution space. Currently, this query process is done by hand, based on the personal experience of analysts. By analogy to the well-known active learning problem in machine learning classification problems, we present a machine-based active learning problem for the subgraph match problem in which the machine suggests optimal template target nodes that would be most likely to reduce the solution space when it is otherwise overly large and complex. The humans in the loop can then include additional information about those target nodes. We present some case studies for both synthetic and real world datasets for multichannel subgraph matching.

Industry 4.0 is now much more than just a buzzword. However, with the advancement of automation through digitization and softwarization of dedicated hardware, applications are also becoming more susceptible to random hardware errors in the calculation. This cyber-physical demonstrator uses a robotic application to show the effects that even single bit flips can have in the real world due to hardware errors. Using the graphical user interface including the human machine interface, the audience can generate hardware errors in the form of bit flips and see their effects live on the robot. In this paper we will be showing a new technology, the SIListra Safety Transformer (SST), that makes it possible to detect those kind of random hardware errors, which can subsequently make safety-critical applications more reliable.

Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints and is set to become part of a multi-billion industry. The resource constraints in this novel network infrastructure tier constricts the deployment of existing Network Intrusion Detection System with Deep Learning models (DLM). We address this issue by developing a novel light, fast and accurate `Edge-Detect' model, which detects Distributed Denial of Service attack on edge nodes using DLM techniques. Our model can work within resource restrictions i.e. low power, memory and processing capabilities, to produce accurate results at a meaningful pace. It is built by creating layers of Long Short-Term Memory or Gated Recurrent Unit based cells, which are known for their excellent representation of sequential data. We designed a practical data science pipeline with Recurring Neural Network to learn from the network packet behavior in order to identify whether it is normal or attack-oriented. The model evaluation is from deployment on actual edge node represented by Raspberry Pi using current cybersecurity dataset (UNSW2015). Our results demonstrate that in comparison to conventional DLM techniques, our model maintains a high testing accuracy of 99% even with lower resource utilization in terms of cpu and memory. In addition, it is nearly 3 times smaller in size than the state-of-art model and yet requires a much lower testing time.

With the explosive growth of IoT applications, billions of things are now connected via edge devices and a colossal volume of data is sent over the internet. Providing security to the user data becomes crucial. The rise in zero-day attacks are a challenge in IoT scenarios. With the large scale of IoT application detection and mitigation of such attacks by the network administrators is cumbersome. The edge device Raspberry pi is remotely logged using Secure Shell (SSH) protocol in 90% of the IoT applications. The case study of SSH brute force attack on the edge device Raspberry pi is demonstrated with experimentation in the IoT networking scenario using Intrusion Detection System (IDS). The IP crawlers available on the internet are used by the attacker to obtain the IP address of the edge device. The proposed system continuously monitors traffic, analysis the log of attack patterns, detects and mitigates SSH brute attack. An attack hijacks and wastes the system resources depriving the authorized users of the resources. With the proposed IDS, we observe 25% CPU conservation, 40% power conservation and 10% memory conservation in resource utilization, as the IDS, mitigates the attack and releases the resources blocked by the attacker.

Aiming at the cyber security problem of the advanced metering infrastructure(AMI), an anomaly detection method based on edge computing framework for the AMI is proposed. Due to the characteristics of the edge node of data concentrator, the data concentrator has the capability of computing a large amount of data. In this paper, distributing the intrusion detection model on the edge node data concentrator of the AMI instead of the metering center, meanwhile, two-way communication of distributed local model parameters replaces a large amount of data transmission. The proposed method avoids the risk of privacy leakage during the communication of data in AMI, and it greatly reduces communication delay and computational time. In this paper, KDDCUP99 datasets is used to verify the effectiveness of the method. The results show that compared with Deep Convolutional Neural Network (DCNN), the detection accuracy of the proposed method reach 99.05%, and false detection rate only gets 0.74%, and the results indicts the proposed method ensures a high detection performance with less communication rounds, it also reduces computational consumption.

The emergence of the 5G network has boosted the advancements in the field of the internet of things (IoT) and edge/cloud computing. We present a novel architecture to detect fire in indoor and outdoor environments, dubbed as EAC-FD, an abbreviation of edge and cloud-based fire detection. Compared with existing frameworks, ours is lightweight, secure, cost-effective, and reliable. It utilizes a hybrid edge and cloud computing framework with Intel neural compute stick 2 (NCS2) accelerator is for inference in real-time with Raspberry Pi 3B as an edge device. Our fire detection model runs on the edge device while also capable of cloud computing for more robust analysis making it a secure system. We compare different versions of SSD-MobileNet architectures with ours suitable for low-end devices. The fire detection model shows a good balance between computational cost frames per second (FPS) and accuracy.

In this work, we have proposed a state-of-the-art face logging system that detects and logs high quality cropped face images of the people in real-time for security applications. Multiple strategies based on resolution, velocity and symmetry of faces have been applied to obtain best quality face images. The proposed system handles the issue of motion blur in the face images by determining the velocities of the detections. The output of the system is the face database, where four faces for each detected person are stored along with the time stamp and ID number tagged to it. The facial features are extracted by our system, which are used to search the person-of-interest instantly. The proposed system has been implemented in a docker container environment on two edge devices: the powerful NVIDIA Jetson TX2 and the cheaper NVIDIA Jetson N ano. The light and fast face detector (LFFD) used for detection, and ResN et50 used for facial feature extraction are optimized using TensorRT over these edge devices. In our experiments, the proposed system achieves the True Acceptance Rate (TAR) of 0.94 at False Acceptance Rate (FAR) of 0.01 while detecting the faces at 20–30 FPS on NVIDIA Jetson TX2 and about 8–10 FPS on NVIDIA Jetson N ano device. The advantage of our system is that it is easily deployable at multiple locations and also scalable based on application requirement. Thus it provides a realistic solution to face logging application as the query or suspect can be searched instantly, which may not only help in investigation of incidents but also in prevention of untoward incidents.

A smart home provides better living environment by allowing remote Internet access for controlling the home appliances and devices. Security of smart homes is an important application area commonly using Passive Infrared Sensors (PIRs), image capture and analysis but such solutions sometimes fail to detect an event. An unambiguous person detection is important for security applications so that no event is missed and also that there are no false alarms which result in waste of resources. Cloud platforms provide deep learning and IoT services which can be used to implement an automated and failsafe security application. In this paper, we demonstrate reliable person detection for indoor and outdoor scenarios by integrating an application running on an edge device with AWS cloud services. We provide results for identifying a person before authorizing entry, detecting any trespassing within the boundaries, and monitoring movements within the home.

In the field of image steganography, edge detection based implantation methods play vital rules in providing stronger security of hided data. In this arena, researcher applies a suitable edge detection method to detect edge pixels in an image. Those detected pixels then conceive secret message bits. A very recent trend is to employ multiple edge detection methods to increase edge pixels in an image and thus to enhance the embedding capacity. The uses of multiple edge detectors additionally boost up the data security. Like as the demand for embedding capacity, many applications need to have the modified image, i.e., stego image, with good quality. Indeed, when the message payload is low, it will not be a better idea to finds more local pixels for embedding that small payload. Rather, the image quality will look better, visually and statistically, if we could choose a part but sufficient pixels to implant bits. In this article, we propose an algorithm that uses multiple edge detection algorithms to find edge pixels separately and then selects pixels which are common to all edges. This way, the proposed method decreases the number of embeddable pixels and thus, increases the image quality. The experimental results provide promising output.

Image edge is considered to be the most important attribute to provide valuable image perception information. At present, video image data is developing towards high resolution and high frame number. The image data processing capacity is huge, so the processing speed is very strict to meet the real-time performance of image data transmission. In this context, we present a method to accelerate the real-time video image edge detection. FPGA is used as the development platform. The real-time edge detection algorithm of image data with 1280x720 resolution and 30 frame/s, combined with median filter, Sobel edge detection algorithm and corrosion expansion algorithm, makes the running time of image processing module shorter. The color image of the video image collected by camera is processed. The HDMI interface shows that the scheme has achieved ideal results in the FPGA hardware platform simulation model, greatly improves the efficiency of the algorithm, and provides a guarantee for the speed and stability of the real-time image processing system.

Internet of Things (IoT) and its applications are becoming commonplace with more devices, but always at risk of network security. It is therefore crucial for an IoT network design to identify attackers accurately, quickly and promptly. Many solutions have been proposed, mainly concerning secure IoT architectures and classification algorithms, but none of them have paid enough attention to reducing the complexity. Our proposal in this paper is an edge-cloud architecture that fulfills the detection task right at the edge layer, near the source of the attacks for quick response, versatility, as well as reducing the cloud's workload. We also propose a multi-attack detection mechanism called LCHA (Low-Complexity detection solution with High Accuracy) , which has low complexity for deployment at the edge zone while still maintaining high accuracy. The performance of our proposed mechanism is compared with that of other machine learning and deep learning methods using the most updated BoT-IoT data set. The results show that LCHA outperforms other algorithms such as NN, CNN, RNN, KNN, SVM, KNN, RF and Decision Tree in terms of accuracy and NN in terms of complexity.

With the popularity of smart devices in the power grid and the advancement of data collection technology, the amount of electricity usage data has exploded in recent years, which is beneficial for optimizing service quality and grid operation. However, current data analysis is mainly based on cloud platforms, which poses challenges to transmission bandwidth, computing resources, and transmission delays. To solve the problem, this paper proposes a graph convolution neural networks (GCNs) based edge-cloud collaborative anomaly detection model. Specifically, the time series is converted into graph data based on visibility graph model, and graph convolutional network model is adopted to classify the labeled graph data for anomaly detection. Then a model segmentation method is proposed to adaptively divide the anomaly detection model between the edge equipment and the back-end server. Experimental results show that the proposed scheme provides an effective solution to edge anomaly detection and can make full use of the computing resources of terminal equipment.

Digital watermarking is the multimedia leading security protection as it permanently escorts the digital content. Image copyright protection is becoming more anxious as the new 5G technology emerged. Protecting images with a robust scheme without distorting them is the main trade-off in digital watermarking. In this paper, a watermarking scheme based on discrete cosine transform (DCT) and singular value decomposition (SVD) using canny edge detector technique is proposed. A binary encrypted watermark is reshaped into a vector and inserted into the edge detected vector from the diagonal matrix of the SVD of DCT DC and low-frequency coefficients. Watermark insertion is performed by using an edge-tracing mechanism. The scheme is evaluated using the Peak Signal to Noise Ratio (PSNR) and Normalized Correlation (NC). Attained results are competitive when compared to present works in the field. Results show that the PSNR values vary from 51 dB to 55 dB.

Recently, smart video surveillance at the edge has become a trend in developing security applications since edge computing enables more image processing tasks to be implemented on the decentralised network note of the surveillance system. As a result, many security applications such as behaviour recognition and prediction, employee safety, perimeter intrusion detection and vandalism deterrence can minimise their latency or even process in real-time when the camera network system is extended to a larger degree. Technically, human detection is a key step in the implementation of these applications. With the advantage of high detection rates, deep learning methods have been widely employed on edge devices in order to detect human objects. However, due to their high computation costs, it is challenging to apply these methods on resource limited edge devices for real-time applications. Inspired by the You Only Look Once (YOLO), residual learning and Spatial Pyramid Pooling (SPP), a novel form of real-time human detection is presented in this paper. Our approach focuses on designing a network structure so that the developed model can achieve a good trade-off between accuracy and processing time. Experimental results show that our trained model can process 2 FPS on Raspberry PI 3B and detect humans with accuracies of 95.05 % and 96.81 % when tested respectively on INRIA and PENN FUDAN datasets. On the human COCO test dataset, our trained model outperforms the performance of the Tiny-YOLO versions. Additionally, compare to the SSD based L-CNN method, our algorithm achieves better accuracy than the other method.

The fusion of infrared and visible images using traditional multi-scale decomposition methods often leads to the loss of detailed information or the blurring of image edges, which is because the contour information and the detailed information within the contour cannot be retained simultaneously in the fusion process. To obtain high-quality fused images, a hybrid multi-scale decomposition fusion method using co-occurrence and Gaussian filters is proposed in this research. At first, by making full use of the smoothing effect of the Gaussian filter and edge protection characteristic of the co-occurrence filter, source images are decomposed into multiple hierarchical structures with different characteristics. Then, characteristics of sub-images at each level are analyzed, and the corresponding fusion rules are designed for images at different levels. At last, the final fused image obtained by combining fused sub-images of each level has rich scene information and clear infrared targets. Compared with several traditional multi-scale fusion algorithms, the proposed method has great advantages in some objective evaluation indexes.

The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural networks (DNNs) and spiking neural networks (SNNs), that offer state-of-the-art results on resource-constrained edge devices is challenging due to the stringent memory and power/energy constraints. Moreover, these systems are required to maintain correct functionality under diverse security and reliability threats. This paper first discusses existing approaches to address energy efficiency, reliability, and security issues at different system layers, i.e., hardware (HW) and software (SW). Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation. To address reliability threats (like permanent and transient faults), we highlight cost-effective mitigation techniques, like fault-aware training and mapping. Moreover, we briefly discuss effective detection and protection techniques to address security threats (like model and data corruption). Towards the end, we discuss how these techniques can be combined in an integrated cross-layer framework for realizing robust and energy-efficient Edge AI systems.

The Internet of Things (IoT) has been growing rapidly in recent years. With the appearance of 5G, it is expected to become even more indispensable to people's lives. In accordance with the increase of Distributed Denial-of-Service (DDoS) attacks from IoT devices, DDoS defense has become a hot research topic. DDoS detection mechanisms executed on routers and SDN environments have been intensely studied. However, these methods have the disadvantage of requiring the cost and performance of the devices. In addition, there is no existing DDoS mitigation algorithm on the network edge that can be performed with the low-cost and low-performance equipment. Therefore, this paper proposes a light-weight DDoS mitigation scheme at the network edge using limited resources of inexpensive devices such as home gateways. The goal of the proposed scheme is to detect and mitigate flooding attacks. It utilizes unused queue resources to detect malicious flows by random shuffling of queue allocation and discard the packets of the detected flows. The performance of the proposed scheme was confirmed via theoretical analysis and computer simulation. The simulation results match the theoretical results and the proposed algorithm can efficiently detect malicious flows using limited resources.

It has been a hot research topic to detect and mitigate Distributed Denial-of-Service (DDoS) attacks due to the significant increase of serious threat of such attacks. The rapid growth of Internet of Things (IoT) has intensified this trend, e.g. the Mirai botnet and variants. To address this issue, a light-weight DDoS mitigation mechanism was presented. In the proposed scheme, flooding attacks are detected by stochastic queue allocation which can be executed with widespread and inexpensive commercial products at a network edge. However, the detection process is delayed when the number of incoming flows is large because of the randomness of queue allocation. Thus, in this paper we propose an efficient queue allocation algorithm for rapid DDoS mitigation using limited resources. The idea behind the proposed scheme is to avoid duplicate allocation by decreasing the randomness of the existing scheme. The performance of the proposed scheme was confirmed via theoretical analysis and computer simulation. As a result, it was confirmed that malicious flows are efficiently detected and discarded with the proposed algorithm.

Digital forensic artifacts aim to provide evidence from digital sources for attributing blame to suspects, assessing their intents, corroborating their statements or alibis, etc. Textual data is a significant source of artifacts, which can take various forms, for instance in the form of communications. E-mails, memos, tweets, and text messages are all examples of textual communications. Complex statistical, linguistic and other scientific procedures can be manually applied to this data to uncover significant clues that point the way to factual information. While expert investigators can undertake this task, there is a possibility that critical information is missed or overlooked. The primary objective of this work is to aid investigators by partially automating the detection of suspicious e-mail deletions. Our approach consists in building a dynamic graph to represent the temporal evolution of communications, and then using a Variational Graph Autoencoder to detect possible e-mail deletions in this graph. Our model uses multiple types of features for representing node and edge attributes, some of which are based on metadata of the messages and the rest are extracted from the contents using natural language processing and text mining techniques. We use the autoencoder to detect missing edges, which we interpret as potential deletions; and to reconstruct their features, from which we emit hypotheses about the topics of deleted messages. We conducted an empirical evaluation of our model on the Enron e-mail dataset, which shows that our model is able to accurately detect a significant proportion of missing communications and to reconstruct the corresponding topic vectors.

In view of the common edge computing-based cloud-side collaborative environment summary existing search key and authentication key sharing caused by data information leakage, this paper proposes a cryptographic search based on public key searchable encryption in an edge computing environment method, this article uses the public key to search for the characteristics of the encryption algorithm, and allows users to manage the corresponding private key. In the process of retrieval and execution, the security of the system can be effectively ensured through the secret trapdoor. Through the comparison of theoretical algorithms, the searchable encryption scheme in the edge computing environment proposed in this paper can effectively reduce the computing overhead on the user side, and complete the over-complex computing process on the edge server or the central server, which can improve the overall efficiency of encrypted search.

Internet of Things (IoT) is penetrating into every aspect of our personal lives including our body, our home and our living environment which poses numerous security challenges. The number of heterogeneous connected devices is increasing exponentially in IoT, which in turn increases the attack surface of IoT. This forces the need for uniform, distributed security mechanism which can efficiently detect the attack at faster rate in highly scalable IoT environment. The proposed work satisfies this requirement by providing a security framework which combines Fog computing and Software Defined Networking (SDN). The experimental results depicts the effectiveness in protecting the IoT applications at faster rate

In recent years, the application of style transfer has become more and more widespread. Traditional deep learning-based style transfer networks often have problems such as image distortion, loss of detailed information, partial content disappearance, and transfer errors. The style transfer network based on deep learning that we propose in this article is aimed at dealing with these problems. Our method uses image edge information fusion and semantic segmentation technology to constrain the image structure before and after the migration, so that the converted image maintains structural consistency and integrity. We have verified that this method can successfully suppress image conversion distortion in most scenarios, and can generate good results.