Biblio

The construction of power Internet of things is an important development direction of power grid enterprises in the future. Big data not only brings economic and social benefits to the power system industry, but also brings many information security problems. Therefore, in the case of accelerating the construction of ubiquitous electric Internet of things, it is urgent to standardize the data security protection in the ubiquitous electric Internet of things environment. By analyzing the characteristics of big data in power system, this paper discusses the security risks faced by big data in power system. Finally, we propose some methods of data security protection based on the defects of big data security in current power system. By building a data security intelligent management and control platform, it can automatically discover and identify the types and levels of data assets, and build a classification and grading information base of dynamic data assets. And through the detection and identification of data labels and data content characteristics, tracking the use of data flow process. So as to realize the monitoring of data security state. By protecting sensitive data against leakage based on the whole life cycle of data, the big data security of power grid informatization can be effectively guaranteed and the safety immunity of power information system can be improved.

Intelligent connected vehicle cyber security has attracted widespread attention this year. The safety of GNSS information is related to the safety of cars and has become a key technology. This paper researches the cyber security characteristics of intelligent connected vehicle navigation and positioning by analyzing the signal receiving mode of navigation and positioning on the vehicle terminal. The article expounds the principles of deceiving and interfering cyber security that lead to the safety of GNSS information. This paper studies the key causes of cyber security. Based on key causes, the article constructs a GNSS cyber security test method by combining a navigation signal simulator and an interference signal generator. The results shows that the method can realize the security test of the GNSS information of the vehicle terminal. This method provides a test method for the navigation terminal defense cyber security capability for a vehicle terminal, and fills a gap in the industry for the vehicle terminal information security test.

The completion and the correction of measurement data are the foundation of the ubiquitous power internet of things construction. However, data missing may occur during the data transporting process. Therefore, a model of missing load situation reconstruction based on the generative adversarial networks is proposed in this paper to overcome the disadvantage of depending on data of other relevant factors in conventional methods. Through the unsupervised training, the proposed model can automatically learn the complex features of loads that are difficult to model explicitly to fill the incomplete load data without using other relevant data. Meanwhile, a method of online correction is put forward to improve the robustness of the reconstruction model in different scenarios. The proposed method is fully data-driven and contains no explicit modeling process. The test results indicate that the proposed algorithm is well-matched for the various scenarios, including the discontinuous missing load reconstruction and the continuous missing load reconstruction even massive data missing. Specifically, the reconstruction error rate of the proposed algorithm is within 4% under the absence of 50% load data.

Cloud computing has been envisioned as a next generation information technology (IT) paradigm. The risk of losing data stored with any untrustworthy service provider is the key barrier to widespread uptake of cloud computing. This paper proposes an algebraic signature based remote data possession checking (RDPC) scheme to verify the integrity of the data stored in the cloud. This scheme integrates forward error-correcting codes to enhance the data possession guarantee, which can recover the data when a small amount of file has been deleted. The scheme allows verification without the need for the auditor to compare against the original data, which reduces the communication complexity dramatically. The storage complexity of cloud user is reduced to several bytes' information. Extensive security analysis and simulation show that the proposed scheme is highly provably secure. Finally, experiment results reveal that the computation performance is effective, and bounded by disk I/O.

Recent work has quantified the degradations that occur in convolutional neural nets (CNN) deployed in harsh environments like space-based image or radio frequency (RF) processing applications. Such degradations yield a robust correlation and causality between single-event upset (SEU) induced errors in memory weights of on-orbit CNN implementations. However, minimal considerations have been given to how the resilience of CNNs can be improved algorithmically as opposed to via enhanced hardware. This paper focuses on RF-processing CNNs and performs an in-depth analysis of applying software-based error detection and correction mechanisms, which may subsequently be combined with protections of radiation-hardened processor platforms. These techniques are more accessible for low cost smallsat platforms than ruggedized hardware. Additionally, methods for minimizing the memory and computational complexity of the resulting resilience techniques are identified. Combined with periodic scrubbing, the resulting techniques are shown to improve expected lifetimes of CNN-based RF-processing algorithms by several orders of magnitude.

A synthetic aperture radar (SAR) target detection method based on the fusion of multiscale superpixel segmentations is proposed in this paper. SAR images are segmented between land and sea firstly by using superpixel technology in different scales. Secondly, image segmentation results together with the constant false alarm rate (CFAR) detection result are coalesced. Finally, target detection is realized by fusing different scale results. The effectiveness of the proposed algorithm is tested on Sentinel-1A data.

The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system. However, manipulated power flow measurements can potentially hide overloads and bypass the bad data detection scheme to interfere the validity of estimated states. In this paper, we use an autoencoder neural network to detect anomalous system states and investigate the impact of hyperparameters on the detection performance for false data injection attacks that target power flows. Experimental results on the IEEE 118 bus system indicate that the proposed mechanism has the ability to achieve satisfactory learning efficiency and detection accuracy.

State estimation is of considerable significance for the power system operation and control. However, well-designed false data injection attacks can utilize blind spots in conventional residual-based bad data detection methods to manipulate measurements in a coordinated manner and thus affect the secure operation and economic dispatch of grids. In this paper, we propose a detection approach based on an autoencoder neural network. By training the network on the dependencies intrinsic in `normal' operation data, it effectively overcomes the challenge of unbalanced training data that is inherent in power system attack detection. To evaluate the detection performance of the proposed mechanism, we conduct a series of experiments on the IEEE 118-bus power system. The experiments demonstrate that the proposed autoencoder detector displays robust detection performance under a variety of attack scenarios.

Due to environmental influence and technology limitation, a wireless sensor/sensors module can neither store or process all raw data locally nor reliably forward it to a destination in heterogeneous IoT environment. As a result, the data collected by the IoT's sensors are inherently noisy, unreliable, and may trigger many false alarms. These false or misleading data can lead to wrong decisions once the data reaches end entities. Therefore, it is highly recommended and desirable to acquire trustworthy data before data transmission, aggregation, and data storing at the end entities/cloud. In this paper, we propose an In-network Generalized Trustworthy Data Collection (IGTDC) framework for trustworthy data acquisition and faulty sensor detection in the IoT environment. The key idea of IGTDC is to allow a sensor's module to examine locally whether the raw data is trustworthy before transmitting towards upstream nodes. It further distinguishes whether the acquired data can be trusted or not before data aggregation at the sink/edge node. Besides, IGTDC helps to recognize a faulty or compromised sensor. For a reliable data collection, we use collaborative IoT technique, gate-level modeling, and programmable logic device (PLD) to ensure that the acquired data is reliable before transmitting towards upstream nodes/cloud. We use a hardware-based technique called “Gray Code” to detect a faulty sensor. Through simulations we reveal that the acquired data in IGTDC framework is reliable that can make a trustworthy data collection for event detection, and assist to distinguish a faulty sensor.

False data injection (FDI) attacks could happen in decode-and-forward (DF) wireless cooperative relay networks. Although physical integrity check (PIC) can combat that by applying physical layer detection, the detector depends on the decoding results and low signal-to-noise ratio (SNR) further deteriorates the detecting results. In this paper, a physical layer detect-before-decode (DbD) method is proposed, which has low computational complexity with no sacrifice of false alarm and miss detection rates. One significant advantage of this method is the detector does not depend on the decoding results. In order to implement the proposed DbD method, a unified error sufficient statistic (UESS) containing the full information of FDI attacks is constructed. The proposed UESS simplifies the detector because it is applicable to all link conditions, which means there is no need to deal each link condition with a specialized sufficient statistic. Moreover, the source to destination outage probability (S2Dop) of the DF cooperative relay network utilizing the proposed DbD method is studied. Finally, numerical simulations verify the good performance of this DbD method.

The state estimation technology is utilized to estimate the grid state based on the data of the meter and grid topology structure. The false data injection attack (FDIA) is an information attack method to disturb the security of the power system based on the meter measurement. Current FDIA detection researches pay attention on detecting its presence. The location information of FDIA is also important for power system security. In this paper, locating the FDIA of the meter is regarded as a multi-label classification problem. Each label represents the state of the corresponding meter. The ensemble model, the multi-label decision tree algorithm, is utilized as the classifier to detect the exact location of the FDIA. This method does not need the information of the power topology and statistical knowledge assumption. The numerical experiments based on the IEEE-14 bus system validates the performance of the proposed method.

Design for trust approaches can protect an MPSoC system from hardware Trojan attack due to the high penetration of third-party intellectual property. However, this incurs significant design cost by purchasing IP cores from various IP vendors, and the IP vendors providing particular IP are always limited, making these approaches unable to be performed in practice. This paper treats IP vendor as constraint, and tasks are scheduled with a minimized security constraint violations, furthermore, the area of MPSoC is also optimized during scheduling. Experimental results demonstrate the effectiveness of our proposed algorithm, by reducing 0.37% security constraint violations.

The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threats to a range of mission-critical deep learning systems and applications. This paper takes a holistic view to characterize the adversarial examples in deep learning by studying their adverse effect and presents an attack-independent countermeasure with three original contributions. First, we provide a general formulation of adversarial examples and elaborate on the basic principle for adversarial attack algorithm design. Then, we evaluate 15 adversarial attacks with a variety of evaluation metrics to study their adverse effects and costs. We further conduct three case studies to analyze the effectiveness of adversarial examples and to demonstrate their divergence across attack instances. We take advantage of the instance-level divergence of adversarial examples and propose strategic input transformation teaming defense. The proposed defense methodology is attack-independent and capable of auto-repairing and auto-verifying the prediction decision made on the adversarial input. We show that the strategic input transformation teaming defense can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false-positive rates, compared to existing representative defense methods.

The trust of a robot in its human partner is a significant issue in human-robot interaction, which is seldom explored in the field of robotics. This study addresses a critical issue of robots' trust in humans during the human-robot collaboration process based on the data of human motions, past interactions of the human-robot pair, and the human's current performance in the co-carry task. The trust level is evaluated dynamically throughout the collaborative task that allows the trust level to change if the human performs false positive actions, which can help the robot avoid making unpredictable movements and causing injury to the human. Experimental results showed that the robot effectively assisted the human in collaborative tasks through the proposed computational trust model.

LoRaWAN (Low-power Wide-Area Networks) is the main specification for application-level IoT (Internet of Things). The current version, published in October 2017, is LoRaWAN 1.1, with its 1.0 precursor still being the main specification supported by commercial devices such as PyCom LoRa transceivers. Prior (semi)-formal investigations into the security of the LoRaWAN protocols are scarce, especially for Lo-RaWAN 1.1. Moreover, amongst these few, the current encodings [4], [9] of LoRaWAN into verification tools unfortunately rely on much-simplified versions of the LoRaWAN protocols, undermining the relevance of the results in practice. In this paper, we fill in some of these gaps. Whilst we briefly discuss the most recent cryptographic-orientated works [5] that looked at LoRaWAN 1.1, our true focus is on producing formal analyses of the security and correctness of LoRaWAN, mechanised inside automated tools. To this end, we use the state-of-the-art prover, Tamarin. Importantly, our Tamarin models are a faithful and precise rendering of the LoRaWAN specifications. For example, we model the bespoke nonce-generation mechanisms newly introduced in LoRaWAN 1.1, as well as the “classical” but shortdomain nonces in LoRaWAN 1.0 and make recommendations regarding these. Whilst we include small parts on device-commissioning and application-level traffic, we primarily scrutinise the Join Procedure of LoRaWAN, and focus on version 1.1 of the specification, but also include an analysis of Lo-RaWAN 1.0. To this end, we consider three increasingly strong threat models, resting on a Dolev-Yao attacker acting modulo different requirements made on various channels (e.g., secure/insecure) and the level of trust placed on entities (e.g., honest/corruptible network servers). Importantly, one of these threat models is exactly in line with the LoRaWAN specification, yet it unfortunately still leads to attacks. In response to the exhibited attacks, we propose a minimal patch of the LoRaWAN 1.1 Join Procedure, which is as backwards-compatible as possible with the current version. We analyse and prove this patch secure in the strongest threat model mentioned above. This work has been responsibly disclosed to the LoRa Alliance, and we are liaising with the Security Working Group of the LoRa Alliance, in order to improve the clarity of the LoRaWAN 1.1 specifications in light of our findings, but also by using formal analysis as part of a feedback-loop of future and current specification writing.

On the current website, there are many undeniable conditions and there is the existence of new plot holes. If data link is normally extracted on each of the websites, it becomes difficult to evaluate each vulnerability, with tolls such as XS S, SQLI, and other such existing tools for vulnerability assessment. Integrated testing criteria for vulnerabilities are met. In addition, the response should be automated and systematic. The primary value of vulnerability Buffer will be made of predefined and self-formatted code written in python, and the software is automated to send reports to their respective users. The vulnerabilities are tried to be classified as accessible. OWASP is the main resource for developing and validating web security processes.

Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed scenario. These deep learning methods use large-scale training data with large complexity. As a solution, in this paper, we show how to use pre-trained convolutional neural net models to perform feature extraction and context mining, and then use denoising autoencoder with relatively low model complexity to provide efficient and accurate surveillance anomaly detection, which can be useful for the resource-constrained devices such as edge devices of the Internet of Things (IoT). Our anomaly detection model makes decisions based on the high-level features derived from the selected embedded computer vision models such as object classification and object detection. Additionally, we derive contextual properties from the high-level features to further improve the performance of our video anomaly detection method. We use two UCSD datasets to demonstrate that our approach with relatively low model complexity can achieve comparable performance compared to the state-of-the-art approaches.

This paper studies initial-value privacy problems of linear dynamical systems. We consider a standard linear time-invariant system with random process and measurement noises. For such a system, eavesdroppers having access to system output trajectories may infer the system initial states, leading to initial-value privacy risks. When a finite number of output trajectories are eavesdropped, we consider a requirement that any guess about the initial values can be plausibly denied. When an infinite number of output trajectories are eavesdropped, we consider a requirement that the initial values should not be uniquely recoverable. In view of these two privacy requirements, we define differential initial-value privacy and intrinsic initial-value privacy, respectively, for the system as metrics of privacy risks. First of all, we prove that the intrinsic initial-value privacy is equivalent to unobservability, while the differential initial-value privacy can be achieved for a privacy budget depending on an extended observability matrix of the system and the covariance of the noises. Next, the inherent network nature of the considered linear system is explored, where each individual state corresponds to a node and the state and output matrices induce interaction and sensing graphs, leading to a network system. Under this network system perspective, we allow the initial states at some nodes to be public, and investigate the resulting intrinsic initial- value privacy of each individual node. We establish necessary and sufficient conditions for such individual node initial-value privacy, and also prove that the intrinsic initial-value privacy of individual nodes is generically determined by the network structure.

In recent years, the computation security of edge computing has been raised as a major concern since the edge devices are often distributed on the edge of the network, less trustworthy than cloud servers and have limited storage/ computation/ communication resources. Recently, coded computing has been proposed to protect the confidentiality of computing data under edge device's independent attack and minimize the total cost (resource consumption) of edge system. In this paper, for the cooperative attack, we design an efficient scheme to ensure the information-theory security (ITS) of user's data and further reduce the total cost of edge system. Specifically, we take matrix multiplication as an example, which is an important module appeared in many application operations. Moreover, we theoretically analyze the necessary and sufficient conditions for the existence of feasible scheme, prove the security and decodeability of the proposed scheme. We also prove the effectiveness of the proposed scheme through considerable simulation experiments. Compared with the existing schemes, the proposed scheme further reduces the total cost of edge system. The experiments also show a trade-off between storage and communication.

Trust relationship prediction among people provides valuable supports for decision making, information dissemination, and product promotion in online social networks. Network embedding has achieved promising performance for link prediction by learning node representations that encode intrinsic network structures. However, most of the existing network embedding solutions cannot effectively capture the properties of a trust network that has directed edges and nodes with in/out links. Furthermore, there usually exist rich user attributes in trust networks, such as ratings, reviews, and the rated/reviewed items, which may exert significant impacts on the formation of trust relationships. It is still lacking a network embedding-based method that can adequately integrate these properties for trust prediction. In this work, we develop an AtNE-Trust model to address these issues. We firstly capture user embedding from both the trust network structures and user attributes. Then we design a deep multi-view representation learning module to further mine and fuse the obtained user embedding. Finally, a trust evaluation module is developed to predict the trust relationships between users. Representation learning and trust evaluation are optimized together to capture high-quality user embedding and make accurate predictions simultaneously. A set of experiments against the real-world datasets demonstrates the effectiveness of the proposed approach.

Intelligenta transportation is an important part of urban development. The core of realizing intelligent transportation is to master the urban road condition. This system processes the video of dashcam based on the Panoptic Segmentation network and adds a tracking module based on the comparison of front and rear frames and KM algorithm. The system mainly includes the following parts: embedded device, Panoptic Feature Pyramid Network, cloud server and Web site.

Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category.

Visual reasoning between visual image and natural language description is a long-standing challenge in computer vision. While recent approaches offer a great promise by compositionality or relational computing, most of them are oppressed by the challenge of training with datasets containing only a limited number of images with ground-truth texts. Besides, it is extremely time-consuming and difficult to build a larger dataset by annotating millions of images with text descriptions that may very likely lead to a biased model. Inspired by the majority success of webly supervised learning, we utilize readily-available web images with its noisy annotations for learning a robust representation. Our key idea is to presume on web images and corresponding tags along with fully annotated datasets in learning with knowledge embedding. We present a two-stage approach for the task that can augment knowledge through an effective embedding model with weakly supervised web data. This approach learns not only knowledge-based embeddings derived from key-value memory networks to make joint and full use of textual and visual information but also exploits the knowledge to improve the performance with knowledge-based representation learning for applying other general reasoning tasks. Experimental results on two benchmarks show that the proposed approach significantly improves performance compared with the state-of-the-art methods and guarantees the robustness of our model against visual reasoning tasks and other reasoning tasks.

Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring expression datasets, however, fail to provide an ideal test bed for evaluating the reasoning ability of the models, mainly because 1) their expressions typically describe only some simple distinctive properties of the object and 2) their images contain limited distracting information. To bridge the gap, we propose a new dataset for visual reasoning in context of referring expression comprehension with two main features. First, we design a novel expression engine rendering various reasoning logics that can be flexibly combined with rich visual properties to generate expressions with varying compositionality. Second, to better exploit the full reasoning chain embodied in an expression, we propose a new test setting by adding additional distracting images containing objects sharing similar properties with the referent, thus minimising the success rate of reasoning-free cross-domain alignment. We evaluate several state-of-the-art REF models, but find none of them can achieve promising performance. A proposed modular hard mining strategy performs the best but still leaves substantial room for improvement.

The Internet of Things technology has been used in a wide range of fields, ranging from industrial applications to individual lives. As a result, a massive amount of sensitive data is generated and transmitted by IoT devices. Those data may be accessed by a large number of complex users. Therefore, it is necessary to adopt an encryption scheme with access control to achieve more flexible and secure access to sensitive data. The Ciphertext Policy Attribute-Based Encryption (CP-ABE) can achieve access control while encrypting data can match the requirements mentioned above. However, the long ciphertext and the slow decryption operation makes it difficult to be used in most IoT devices which have limited memory size and computing capability. This paper proposes a modified CP-ABE scheme, which can implement the full security (adaptive security) under the access structure of AND gate. Moreover, the decryption overhead and the length of ciphertext are constant. Finally, the analysis and experiments prove the feasibility of our scheme.