Biblio

Network embedding, which aims to map the discrete network topology to a continuous low-dimensional representation space with the major topological properties preserved, has emerged as an essential technique to support various network inference tasks. However, incorporating both the evolutionary nature and the network's heterogeneity remains a challenge for existing network embedding methods. In this study, we propose a novel Translation-Based Dynamic Heterogeneous Network Embedding (TransDHE) approach to consider both the aspects simultaneously. For a dynamic heterogeneous network with a sequence of snapshots and multiple types of nodes and edges, we introduce a translation-based embedding module to capture the heterogeneous characteristics (e.g., type information) of each single snapshot. An orthogonal alignment module and RNN-based aggregation module are then applied to explore the evolutionary patterns among multiple successive snapshots for the final representation learning. Extensive experiments on a set of real-world networks demonstrate that TransDHE can derive the more informative embedding result for the network dynamic and heterogeneity over state-of-the-art network embedding baselines.

With the paradigm shift to cloud-based operations, reliable and secure access to and transfer of data between differing security domains has never been more essential. A Cross Domain Solution (CDS) is a guarded interface which serves to execute the secure access and/or transfer of data between isolated and/or differing security domains defined by an administrative security policy. Cross domain security requires trustworthiness at the confluence of the hardware and software components which implement a security policy. Security components must be relied upon to defend against widely encompassing threats – consider insider threats and nation state threat actors which can be both onsite and offsite threat actors – to information assurance. Current implementations of CDS systems use suboptimal Trusted Computing Bases (TCB) without any formal verification proofs, confirming the gap between blind trust and trustworthiness. Moreover, most CDSs are exclusively operated by Department of Defense agencies and are not readily available to the commercial sectors, nor are they available for independent security verification. Still, more CDSs are only usable in physically isolated environments such as Sensitive Compartmented Information Facilities and are inconsistent with the paradigm shift to cloud environments. Our purpose is to address the question of how trustworthiness can be implemented in a remotely deployable CDS that also supports availability and accessibility to all sectors. In this paper, we present a novel CDS system architecture which is the first to use a formally verified TCB. Additionally, our CDS model is the first of its kind to utilize a computation-isolation approach which allows our CDS to be remotely deployable for use in cloud-based solutions.

Most present reconfiguration methods in sharding blockchains rely on a secure randomness, whose generation might be complicated. Besides, a reference committee is usually in charge of the reconfiguration, making the process not decentralized. To address the above issues, this paper proposes a secure and decentralized shard reconfiguration protocol, which allows each shard to complete the selection and confirmation of its own shard members in turn. The PoW mining puzzle is calculated using the public key hash value in the member list confirmed by the last shard. Through the mining and shard member list commitment process, each shard can update its members safely and efficiently once in a while. Furthermore, it is proved that our protocol satisfies the safety, consistency, liveness, and decentralization properties. The honest member proportion in each confirmed shard member list is guaranteed to exceed a certain safety threshold, and all honest nodes have an identical view on the list. The reconfiguration is ensured to make progress, and each node has the same right to participate in the process. Our secure and decentralized shard reconfiguration protocol could be applied to all committee-based sharding blockchains.

Aimed at the high requirement of timeliness in the process of information assurance, this paper describes the average time delay of information transmission in the system, and designs a timeliness index that can quantitatively describe the ability of early warning information assurance. In response to the problem that system capability cannot meet operational requirements due to enemy attacks, this paper analyzes the structure of the early warning information system, Early warning information complex network model is established, based on the timeliness index, a genetic algorithm based on simulated annealing with special chromosome coding is proposed.the algorithm is used to adjust the network model structure, the ability of early warning information assurance has been improved. Finally, the simulation results show the effectiveness of the proposed method.

To meet the application need of dynamic visualization VR display of 3D time-varying field, this paper designed an immersive visualization VR system of 3D time-varying field based on the Unity 3D framework. To reduce visual confusion caused by 3D time-varying field flow line drawing and improve the quality and efficiency of visualization rendering drawing, deep learning was used to extract features from the mesoscale vortex of the 3D time-varying field. Moreover, the 3D flow line dynamic visualization drawing was implemented through the Unity Visual Effect Graph particle system.

The transmission and storage process for the power data in an intelligent grid has problems such as a single point of failure in the central node, low data credibility, and malicious manipulation or data theft. The characteristics of decentralization and tamper-proofing of blockchain and its distributed storage architecture can effectively solve malicious manipulation and the single point of failure. However, there are few safe and reliable data transmission methods for the significant number and various identities of users and the complex node types in the power blockchain. Thus, this paper proposes a collaborative control scheme between on-chain and off-chain power data based on the distributed oracle technology. By building a trusted on-chain transmission mechanism based on distributed oracles, the scheme solves the credibility problem of massive data transmission and interactive power data between smart contracts and off-chain physical devices safely and effectively. Analysis and discussion show that the proposed scheme can realize the collaborative control between on-chain and off-chain data efficiently, safely, and reliably.

The automatic detection of vulnerabilities in Web applications using taint analysis is a hot topic. However, existing taint analysis methods for sanitizers identification are too simple to find available taint transmission chains effectively. These methods generally use pre-constructed dictionaries or simple keywords to identify, which usually suffer from large false positives and false negatives. No doubt, it will have a greater impact on the final result of the taint analysis. To solve that, we summarise and classify the commonly used sanitizers in Web applications and propose an identification method based on semantic analysis. Our method can accurately and completely identify the sanitizers in the target Web applications through static analysis. Specifically, we analyse the natural semantics and program semantics of existing sanitizers, use semantic analysis to find more in Web applications. Besides, we implemented the method prototype in PHP and achieved a vulnerability detection tool called VulChecker. Then, we experimented with some popular open-source CMS frameworks. The results show that Vulchecker can accurately identify more sanitizers. In terms of vulnerability detection, VulChecker also has a lower false positive rate and a higher detection rate than existing methods. Finally, we used VulChecker to analyse the latest PHP applications. We identified several new suspicious taint data propagation chains. Before the paper was completed, we have identified four unreported vulnerabilities. In general, these results show that our approach is highly effective in improving vulnerability detection based on taint analysis.

In recent years, the development of deep learning has brought new ideas to internal threat detection. In this paper, three common deep learning algorithms for threat detection are optimized and innovated, and feature embedding, drift detection and sample weighting are introduced into FCNN. Adaptive multi-iteration method is introduced into Support Vector Data Description (SVDD). A dynamic threshold adjustment mechanism is introduced in VAE. In threat detection, three methods are used to detect the abnormal behavior of users, and the intersection of output results is taken as the final threat judgment basis. Experiments on cert r6.2 data set show that this method can significantly reduce the false positive rate.

The security of Internet of Things (IoT) devices has become a matter of great concern in recent years. The existence of security holes in the executable programs in the IoT devices has resulted in difficult to estimate security risks. For a long time, vulnerability detection is mainly completed by manual debugging and analysis, and the detection efficiency is low and the accuracy is difficult to guarantee. In this paper, the mainstream automated vulnerability analysis methods in recent years are studied, and a vulnerability detection algorithm based on symbol execution is presented. The detection algorithm is suitable for lightweight applications in small and medium-sized IoT devices. It realizes three functions: buffer overflow vulnerability detection, encryption reliability detection and protection state detection. The robustness of the detection algorithm was tested in the experiment, and the detection of overflow vulnerability program was completed within 2.75 seconds, and the detection of encryption reliability was completed within 1.79 seconds. Repeating the test with multiple sets of data showed a small difference of less than 6.4 milliseconds. The results show that the symbol execution detection algorithm presented in this paper has high detection efficiency and more robust accuracy and robustness.

This paper investigates the optimization of physical layer security in multiple-input multiple-output (MIMO) enabled visible light communication (VLC) networks. In the considered model, one transmitter equipped with light-emitting diodes (LEDs) intends to send confidential messages to legitimate users while one eavesdropper attempts to eavesdrop on the communication between the transmitter and legitimate users. This security problem is formulated as an optimization problem whose goal is to minimize the sum mean-square-error (MSE) of all legitimate users while meeting the MSE requirement of the eavesdropper thus ensuring the security. To solve this problem, the original optimization problem is first transformed to a convex problem using successive convex approximation. An iterative algorithm with low complexity is proposed to solve this optimization problem. Simulation results show that the proposed algorithm can reduce the sum MSE of legitimate users by up to 40% compared to a conventional zero forcing scheme.

Recently, the physical layer security (PLS) is becoming an important research area for visible light communication (VLC) systems. In this paper, the secrecy rate performance is investigated for an indoor multi-user visible light communication (VLC) system using artificial noise (AN). In the considered model, all users simultaneously communicate with the legitimate receiver under wiretap channels. The legitimate receiver uses the minimum mean squared error (MMSE) equalizer to detect the received signals. Both lower bound and upper bound of the secrecy rate are obtained for the case that users' signals are uniformly distributed. Simulation results verify the theoretical findings and show the system secrecy rate performance for various positions of illegal eavesdropper.

Data security and privacy have become an important problem while big data systems are growing dramatically fast in various application fields. Paillier additive homomorphic cryptosystem is widely used in information security fields such as big data security, communication security, cloud computing security, and artificial intelligence security. However, how to improve its computational performance is one of the most critical problems in practice. In this paper, we propose two modifications to improve the performance of the Paillier cryptosystem. Firstly, we introduce a key generation method to generate the private key with low Hamming weight, and this can be used to accelerate the decryption computation of the Paillier cryptosystem. Secondly, we propose an acceleration method based on Hensel lifting in the Paillier cryptosystem. This method can obtain a faster and improved decryption process by showing the mathematical analysis of the decryption algorithm.

Autonomous vehicles increasingly exploit computer-vision-based object detection systems to perceive environments and make critical driving decisions. To increase the quality of images, image stabilizers with inertial sensors are added to alleviate image blurring caused by camera jitters. However, such a trend opens a new attack surface. This paper identifies a system-level vulnerability resulting from the combination of the emerging image stabilizer hardware susceptible to acoustic manipulation and the object detection algorithms subject to adversarial examples. By emitting deliberately designed acoustic signals, an adversary can control the output of an inertial sensor, which triggers unnecessary motion compensation and results in a blurred image, even if the camera is stable. The blurred images can then induce object misclassification affecting safety-critical decision making. We model the feasibility of such acoustic manipulation and design an attack framework that can accomplish three types of attacks, i.e., hiding, creating, and altering objects. Evaluation results demonstrate the effectiveness of our attacks against four academic object detectors (YOLO V3/V4/V5 and Fast R-CNN), and one commercial detector (Apollo). We further introduce the concept of AMpLe attacks, a new class of system-level security vulnerabilities resulting from a combination of adversarial machine learning and physics-based injection of information-carrying signals into hardware.

How to analyze users' data without compromising individual privacy is an important issue in cloud computing. In order to protect privacy and enable the cloud to perform computing, users can apply homomorphic encryption schemes to their data. Most of existing homomorphic encryption-based cloud computing methods require that users' data are encrypted with the same key. While in practice, different users may prefer to use different keys. In this paper, we propose a privacy-preserving cloud computing method which adopts a double-trapdoor homomorphic encryption scheme to deal with the multi-key issue. The proposed method uses two cloud servers to analyze users' encrypted data. And we propose to use blockchain to monitor the information exchanged between the servers. Security analysis shows that the introduction of blockchain can help to prevent the two servers from colluding with each other, hence data privacy is further enhanced. And we conduct simulations to demonstrate the feasibility of the propose method.

Underwater acoustic sensor networks (UASNs) have been receiving more and more attention due to their wide applications and the marine data collection is one of the important applications of UASNs. However, the openness and unreliability of underwater acoustic communication links and the easy capture of underwater wireless devices make UASNs vulnerable to various attacks. On the other hand, due to the limited resources of underwater acoustic network nodes, the high bit error rates, large and variable propagation delays, and low bandwidth of acoustic channels, many mature security mechanisms in terrestrial wireless sensor networks cannot be applied in the underwater environment [1]. In this paper, a secure communication protocol for marine data collection was proposed to ensure the confidentiality and data integrity of communication between under sensor nodes and the sink node in UASNs.

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.

This paper presents some of our first experiences and findings in the ARPA-E project ReNew100, which is to develop an operator support system to enable stable operation of power system with 100% non-synchronous (NS) generation. The key to 100% NS system, as found in many recent studies, is to establish the grid frequency reference using grid-forming (GFM) inverters. In this paper, we demonstrate in Electro-Magnetic-Transient (EMT) simulations, based on Hawai'i big island system with 100% NS capacity, that a system can be operated stably with the help of GFM inverters and appropriate controller parameters for the inverters. The dynamic security optimization (DSO) is introduced for optimizing the inverter control parameters to improve stability of the system towards N-1 contingencies. DSO is verified for five critical N-1 contingencies of big island system identified by Hawaiian Electric. The simulation results show significant stability improvement from DSO. The results in this paper share some insight, and provide a promising solution for operating grid in general with high penetration or 100% of NS generation.

The correctness of security control system strategy is very important to ensure the stability of power system. Aiming at the problem that the current security control strategy verification method is not enough to match the increasingly complex large power grid, this paper proposes a cyclic verification method of security control system strategy table based on constraints and whole process dynamic simulation. Firstly, the method is improved based on the traditional security control strategy model to make the strategy model meet certain generalization ability; And on the basis of this model, the cyclic dynamic verification of the strategy table is realized based on the constraint conditions and the whole process dynamic simulation, which not only ensures the high accuracy of strategy verification for the security control strategy of complex large power grid, but also ensures that the power system is stable and controllable. Finally, based on a certain regional power system, the optimal verification of strategy table verification experiment is realized. The experimental results show that the average processing time of the proposed method is 10.32s, and it can effectively guarantee the controllability and stability of power grid.

This paper studies the secure computation offloading for multi-user multi-server mobile edge computing (MEC)-enabled internet of things (IoT). A novel jamming signal scheme is designed to interfere with the decoding process at the Eve, but not impair the uplink task offloading from users to APs. Considering offloading latency and secrecy constraints, this paper studies the joint optimization of communication and computation resource allocation, as well as partial offloading ratio to maximize the total secrecy offloading data (TSOD) during the whole offloading process. The considered problem is nonconvex, and we resort to block coordinate descent (BCD) method to decompose it into three subproblems. An efficient iterative algorithm is proposed to achieve a locally optimal solution to power allocation subproblem. Then the optimal computation resource allocation and offloading ratio are derived in closed forms. Simulation results demonstrate that the proposed algorithm converges fast and achieves higher TSOD than some heuristics.

Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by the intended owner of the resulting model. By avoiding the need to transport the training data to the central server, federated learning improves privacy and efficiency. But it raises the risk of model theft by clients because the resulting model is available on every client device. Even if the application software used for local training may attempt to prevent direct access to the model, a malicious client may bypass any such restrictions by reverse engineering the application software. Watermarking is a well-known deterrence method against model theft by providing the means for model owners to demonstrate ownership of their models. Several recent deep neural network (DNN) watermarking techniques use backdooring: training the models with additional mislabeled data. Backdooring requires full access to the training data and control of the training process. This is feasible when a single party trains the model in a centralized manner, but not in a federated learning setting where the training process and training data are distributed among several client devices. In this paper, we present WAFFLE, the first approach to watermark DNN models trained using federated learning. It introduces a retraining step at the server after each aggregation of local models into the global model. We show that WAFFLE efficiently embeds a resilient watermark into models incurring only negligible degradation in test accuracy (-0.17%), and does not require access to training data. We also introduce a novel technique to generate the backdoor used as a watermark. It outperforms prior techniques, imposing no communication, and low computational (+3.2%) overhead$^\textrm1$$^\textrm1$\$The research report version of this paper is also available in https://arxiv.org/abs/2008.07298, and the code for reproducing our work can be found at https://github.com/ssg-research/WAFFLE.

Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people’s lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection.

With the rapid development of the Internet, network traffic is becoming more complex and diverse. At the same time, malicious traffic is growing. This seriously threatens the security of networks and information. However, the current DPI (Deep Packet Inspect) engine based on x86 architecture is slow in monitoring speed, which cannot meet the needs. Generally, two factors affect the detection rate: CPU and memory; The efficiency of data packet acquisition, and multi regular expression matching. Under these circumstances, this paper presents an efficient implementation of the DPI engine based on a generic x86 platform. DPDK is used as the platform of network data packets acquisition and processing. Using the multi-queue of the NIC (network interface controller) and the customized symmetric RSS key, the network traffic is divided and reorganized in the form of conversation. The core of traffic identification is hyperscan, which uses a flow pattern to match the packets load of a single conversation efficiently. It greatly reduces memory requirements. The method makes full use of the system resources and takes into account the advantages of high efficiency of hardware implementation. And it has a remarkable improvement in the efficiency of recognition.

Radio frequency (RF) signal classification has significantly been used for detecting and identifying the features of unknown unmanned aerial vehicles (UAVs). This paper proposes a method using empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD) on extracting the communication channel characteristics of intruding UAVs. The decomposed intrinsic mode functions (IMFs) except noise components are selected for RF signal pattern recognition based on machine learning (ML). The classification results show that the denoising effects introduced by EMD and EEMD could both fit in improving the detection accuracy with different features of RF communication channel, especially on identifying time-varying RF signal sources.

Power quality gains more and more attentions because disturbances in power quality may damage equipment security, power availability and system reliability in power system. Detection and classification of the power quality disturbances is the first step before taking measures to lessen their harmful effects. Common methods to classify power quality disturbances includes signal processing methods, machine learning methods and deep learning methods. Signal processing methods are good at feature extraction, while machine learning methods and deep learning methods are expert in multi-classification tasks. Via combing their respective advantages, this paper proposes a combined method based on variational mode decomposition and convolutional neural networks, which needs a small quantity of samples but achieves high classification precision. The proposed method is proved to be a qualified and competitive scheme for the detection and classification of power quality disturbances.

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.