Biblio

DNN models have suffered from adversarial example attacks, which lead to inconsistent prediction results. As opposed to the gradient-based attack, which assumes white-box access to the model by the attacker, we focus on more realistic input perturbations from the real-world and their actual impact on the model robustness without any presence of the attackers. In this work, we promote a standardized framework to quantify the robustness against real-world threats. It is composed of a set of safety properties associated with common violations, a group of metrics to measure the minimal perturbation that causes the offense, and various criteria that reflect different aspects of the model robustness. By revealing comparison results through this framework among 13 pre-trained ImageNet classifiers, three state-of-the-art object detectors, and three cloud-based content moderators, we deliver the status quo of the real-world model robustness. Beyond that, we provide robustness benchmarking datasets for the community.

With the development of smart grid technologies and the fast adoption of household IoT devices in recent years, new threats, attacks, and security challenges arise. While a large number of vulnerabilities, threats, attacks and controls have been discussed in the literature, there lacks an abstract and generalizable framework that can be used to model the cyber-physical interactions of attacks and guide the design of defense mechanisms. In this paper, we propose a new modeling approach for security attacks in smart grids and IoT devices using a Cyber-Physical Systems (CPS) perspective. The model considers both the cyber and physical aspects of the core components of the smart grid system and the household IoT devices, as well as the interactions between the components. In particular, our model recognizes the two parallel attack channels via the cyber world and the physical world, and identifies the potential crossing routes between these two attack channels. We further discuss all possible attack surfaces, attack objectives, and attack paths in this newly proposed model. As case studies, we examine from the perspective of this new model three representative attacks proposed in the literature. The analysis demonstrates the applicability of the model, for instance, to assist the design of detection and defense mechanisms against smart grid cyber-attacks.

False data injection attack (FDIA) is a real threat to smart grids due to its wide range of vulnerabilities and impacts. Designing a proper detection scheme for FDIA is the 1stcritical step in defending the attack in smart grids. In this paper, we investigate two main statistical techniques-based approaches in this regard. The first is based on the principal component analysis (PCA), and the second is based on the canonical correlation analysis (CCA). The test cases illustrate a better characterization performance of FDIA using CCA compared to the PCA. Further, CCA provides a better differentiation of FDIA from normal grid contingencies. On the other hand, PCA provides a significantly reduced false alarm rate.

When modeling information security systems (ISS), the vast majority of works offer various models of threats to the object of protection (threat trees, Petri nets, etc.). However, ISS is not only a mean to prevent threats or reduce damage from their implementation, but also other components - the qualifications of employees responsible for IS, the internal climate in the team, the company's position on the market, and many others. The article considers the cognitive model of the state of the information security system of an average organization. The model is a weighted oriented graph, its' vertices are standard elements of the organization's information security system. The most significant factors affecting the condition of information security of the organization are identified based on the model. Influencing these factors is providing the most effect if IS level.

Cyber-Physical Systems (CPS) such as intelligent connected vehicles, smart farming and smart logistics are constantly generating tons of data and requiring real-time data processing capabilities. Therefore, Edge Computing which provisions computing resources close to the End Devices from the network edge is becoming the ideal platform for CPS. However, it also brings many issues and one of the most prominent challenges is how to ensure the development of trustworthy smart services given the dynamic and distributed nature of Edge Computing. To tackle this challenge, this paper proposes a novel Federated Learning based Edge Computing platform for CPS, named “FengHuoLun”. Specifically, based on FengHuoLun, we can: 1) implement smart services where machine learning models are trained in a trusted Federated Learning framework; 2) assure the trustworthiness of smart services where CPS behaviours are tested and monitored using the Federated Learning framework. As a work in progress, we have presented an overview of the FengHuoLun platform and also some preliminary studies on its key components, and finally discussed some important future research directions.

A non-predicted and transient malfunctioning of one or multiple unmanned aerial vehicles (UAVs) is something that may happen over a course of their deployment. Therefore, it is very important to have means to detect these events and take actions for ensuring a high level of reliability, security, and safety of the flight for the predefined mission. In this research, we propose algorithms aiming at the detection and isolation of any faulty UAV so that the performance of the UAVs application is kept at its highest level. To this end, we propose the use of Kullback-Leiler Divergence (KLD) and Artificial Neural Network (ANN) to build algorithms that detect and isolate any faulty UAV. The proposed methods are declined in these two directions: (1) we compute a difference between the internal and external data, use KLD to compute dissimilarities, and detect the UAV that transmits erroneous measurements. (2) Then, we identify the faulty UAV using an ANN model to classify the sensed data using the internal sensed data. The proposed approaches are validated using a real dataset, provided by the Air Lab Failure and Anomaly (ALFA) for UAV fault detection research, and show promising performance.

Knowledge Tracing (KT) is a task that aims to assess students' mastery level of knowledge and predict their performance over questions, which has attracted widespread attention over the years. Recently, an increasing number of researches have applied deep learning techniques to knowledge tracing and have made a huge success over traditional Bayesian Knowledge Tracing methods. Most existing deep learning-based methods utilized either Recurrent Neural Networks (RNNs) or Convolutional Neural Networks (CNNs). However, it is worth noticing that these two sorts of models are complementary in modeling abilities. Thus, in this paper, we propose a novel knowledge tracing model by taking advantage of both two models via combining them into a single integrated model, named Convolutional Recurrent Knowledge Tracing (CRKT). Extensive experiments show that our model outperforms the state-of-the-art models in multiple KT datasets.

Empirical analysis of source code of Android Fluoride Bluetooth stack demonstrates a novel approach of classification of source code and rating for vulnerability. A workflow that combines deep learning and combinatorial techniques with a straightforward random forest regression is presented. Two kinds of embedding are used: code2vec and LSTM, resulting in a distance matrix that is interpreted as a (combinatorial) graph whose vertices represent code components, functions and methods. Cluster Editing is then applied to partition the vertex set of the graph into subsets representing nearly complete subgraphs. Finally, the vectors representing the components are used as features to model the components for vulnerability risk.

Honeypots are the information system resources used for capturing and analysis of cyber attacks. Highinteraction Honeypots are capable of capturing attacks in their totality and hence are an ideal choice for capturing multi-stage cyber attacks. The term multi-stage attack is an abstraction that refers to a class of cyber attacks consisting of multiple attack stages. These attack stages are executed either by malicious codes, scripts or sometimes even inbuilt system tools. In the work presented in this paper we have proposed a framework for capturing, analysis and modelling of multi-stage cyber attacks. The objective of our work is to devise an effective mechanism for the classification of multi-stage cyber attacks. The proposed framework comprise of a network of high interaction honeypots augmented with an attack analysis engine. The analysis engine performs rule based labeling of captured honeypot data. The labeling engine labels the attack data as generic events. These events are further fused to generate attack graphs. The hence generated attack graphs are used to characterize and later classify the multi-stage cyber attacks.

With the continuous growth of Internet technology and the increasingly broadening applications of The Internet, network security incidents as well as cyber-attacks are also showing a growing trend. Consequently, computer network security is becoming increasingly important. TCP firewall is a computer network security system, and it allows or denies the transmission of data according to specific rules for providing security for the computer network. Traditional firewalls rely on network administrators to set security rules for them, and network administrators sometimes need to choose to allow and deny packets to keep computer networks secure. However, due to the huge amount of data on the Internet, network administrators have a huge task. Therefore, it is particularly important to solve this problem by using the machine learning method of computer technology. This study aims to predict TCP security action based on the TCP transmission characteristics dataset provided by UCI machine learning repository by implementing machine learning models such as neural network, support vector machine (SVM), AdaBoost, and Logistic regression. Processes including evaluating various models and interpretability analysis. By utilizing the idea of ensemble-learning, the final result has an accuracy score of over 98%.

Countries are putting cyber-security at the forefront of their national issues. With the increase in cyber capabilities and infrastructure systems becoming cyber-enabled, threats now have a physical impact from the cyber dimension. This paper proposes an analytical framework for national cyber-security profiling by taking national governmental and technical threat modeling simulations. Applying thematic analysis towards national cybersecurity strategy helps further develop understanding, in conjunction with threat modeling methodology simulation, to gain insight into critical infrastructure threat impact.

The deployment of datasets in the heterogeneous edge-cloud computing paradigm has received increasing attention in state-of-the-art research. However, due to their large sizes and the existence of private scientific datasets, finding an optimal data placement strategy that can minimize data transmission as well as improve performance, remains a persistent problem. In this study, the advantages of both edge and cloud computing are combined to construct a data placement model that works for multiple scientific workflows. Apparently, the most difficult research challenge is to provide a data placement strategy to consider shared datasets, both within individual and among multiple workflows, across various geographically distributed environments. According to the constructed model, not only the storage capacity of edge micro-datacenters, but also the data transfer between multiple clouds across regions must be considered. To address this issue, we considered the characteristics of this model and identified the factors that are causing the transmission delay. The authors propose using a discrete particle swarm optimization algorithm with differential evolution (DE-DPSO) to distribute dataset during workflow execution. Based on this, a new data placement strategy named DE-DPSO-DPS is proposed. DE-DPSO-DPS is evaluated using several experiments designed in simulated heterogeneous edge-cloud computing environments. The results demonstrate that our data placement strategy can effectively reduce the data transmission time and achieve superior performance as compared to traditional strategies for data-sharing scientific workflows.

The use of modeling techniques such as Knuth's Rule or Bayesian Blocks for the purposes of real-time traffic characterization in RFID networks has been proposed already. This study examines the applicability of using Voronoi polygon maps or alternatively, DBSCAN clustering, as initial density estimation techniques when computing 2-Dimentional Bayesian Blocks models of RFID traffic. Our results are useful for the purposes of extending the constant-piecewise adaptation of Bayesian Blocks into 2D piecewise models for the purposes of more precise detection of anomalies in RFID traffic based on multiple log features such as command type, location, UID values, security support, etc. Automatic anomaly detection of RFID networks is an essential first step in the implementation of intrusion detection as well as a timely response to equipment malfunction such as tag hardware failure.

Certificateless signcryption mechanism can not only provide security services, such as message integrity, non-repudiation and confidentiality, but also solve the problems of public key certificate management and key escrow. Zhou et al. proposed a certificateless signcryption mechanism without bilinear mapping and gave its security proof under the discrete logarithm problem and the computational Diffie Hellman problem in the random oracle model. However, the analysis show that this scheme has security flaws. That is, attackers can forge legitimate signatures of any messages. Finally, we give the specific attack process.

Finding a free path without obstacles or situation that pose minimal risk is critical for safe navigation. People who are sighted and people who are blind or visually impaired require navigation safety while walking on a sidewalk. In this paper we develop assistive navigation on a sidewalk by integrating sensory inputs using reinforcement learning. We train the reinforcement model in a simulated robotic environment which is used to avoid sidewalk obstacles. A conversational agent is built by training with real conversation data. The reinforcement learning model along with a conversational agent improved the obstacle avoidance experience about 2.5% from the base case which is 78.75%.

Integrated with various electronic control units (ECUs), vehicles are becoming more intelligent with the assistance of essential connections. However, the interaction with the outside world raises great concerns on cyber-attacks. As a main standard for in-vehicle network, Controller Area Network (CAN) does not have any built-in security mechanisms to guarantee a secure communication. This increases risks of denial of service, remote control attacks by an attacker, posing serious threats to underlying vehicles, property and human lives. As a result, it is urgent to develop an effective in-vehicle network intrusion detection system (IDS) for better security. In this paper, we propose a Feature-based Sliding Window (FSW) to extract the feature of CAN Data Field and CAN IDs. Then we construct a convolutional encoder network (CEN) to detect network intrusion of CAN networks. The proposed FSW-CEN method is evaluated on real-world datasets. The experimental results show that compared to traditional data processing methods and convolutional neural networks, our method is able to detect attacks with a higher accuracy in terms of detection accuracy and false negative rate.

Nowadays, industrial control systems are increasingly subject to cyber-attacks. In this regard, the relevance of ICS modeling for security research and for teaching employees the basics of information security is increasing. Most of the existing testbeds for research on information security of industrial control systems are software and hardware solutions that contain elements of industrial equipment. However, when implementing distance-learning programs, it is not possible to fully use such testbeds. This paper describes the approach of complete virtualization of technological processes in ICS based on the open source programmable logic controller OpenPLC. This enables a complete information security training from any device with Internet access. A unique feature of this stand is also the support of several PLCs and a lower-level subsystem implemented by a distributed I/O system. The study describes the implementation scheme of the stand, and several case of reproduction of attacks. Scaling approaches for this solution are also considered.

Cloud computing is applied in various domains, among which social recommender systems are well-received because of their effectivity to provide suggestions for users. Social recommender systems perform well in alleviating cold start problem, but it suffers from shilling attack due to its natural openness. Shilling attack is an injection attack mainly acting on the training process of machine learning, which aims to advance or suppress the recommendation ranking of target items. Some researchers have studied the influence of shilling attacks in two perspectives simultaneously, which are user-item's rating and user-user's relation. However, they take more consideration into user-item's rating, and up to now, the construction of user-user's relation has not been explored in depth. To explore shilling attacks with complex relations, in this paper, we propose two novel attack models based on triangle relations in social networks. Furthermore, we explore the influence of these models on five social recommendation algorithms. The experimental results on three datasets show that the recommendation can be affected by the triangle relation attacks. The attack model combined with triangle relation has a better attack effect than the model only based on rating injection and the model combined with random relation. Besides, we compare the functions of triangle relations in friend recommendation and product recommendation.

This paper puts forward a formalized method of emergency plan based on ontology, sums up the main concepts such as system, event, rule, measure, constraint and resource, and analyzes the logical relationship among concepts. A digital intelligent emergency plan storage scheme based on relational database model is proposed. In this paper, full-text search, data search and knowledge search are comprehensively used to adapt to the information needs and characteristics of different users' query plans. Finally, an example of emergency plan made by a power supply company is given to illustrate the effectiveness of the method.

The solution of using existing WiFi devices for measurement and maintenance, and establishing a WiFi fingerprint database for precise localization has become a popular method for indoor localization. The traditional WiFi fingerprint privacy protection scheme increases the calculation amount of the client, but cannot completely protect the security of the client and the fingerprint database. In this paper, we make use of WiFi devices to present a Practical Privacy Protection Scheme In WiFi Fingerprint-based Localization PPWFL. In PPWFL, the localization server establishes a pre-partition in the fingerprint database through the E-M clustering algorithm, we divide the entire fingerprint database into several partitions. The server uses WiFi fingerprint entries with partitions as training data and trains a machine learning model. This model can accurately predict the client's partition based on fingerprint entries. The client uses the trained machine learning model to obtain its partition location accurately, picks up WiFi fingerprint entries in its partition, and calculates its geographic location with the localization server through secure multi-party computing. Compared with the traditional solution, our solution only uses the WiFi fingerprint entries in the client's partition rather than the entire fingerprint database. PPWFL can reduce not only unnecessary calculations but also avoid accidental errors (Unexpected errors in fingerprint similarity between non-adjacent locations due to multipath effects of electromagnetic waves during the propagation of complex indoor environments) in fingerprint distance calculation. In particular, due to the use of Secure Multi-Party Computation, most of the calculations are performed in the local offline phase, the client only exchanges data with the localization server during the distance calculation phase. No additional equipment is needed; our solution uses only existing WiFi devices in the building to achieve fast localization based on privacy protection. We prove that PPWFL is secure under the honest but curious attacker. Experiments show that PPWFL achieves efficiency and accuracy than the traditional WiFi fingerprint localization scheme.

Much research is concentrated on improving models for host-based intrusion detection systems (HIDS). Typically, such research aims at improving a model's results (e.g., reducing the false positive rate) in the familiar static training/testing environment using the standard data sources. Matching advancements in the machine learning community, researchers in the syscall HIDS domain have developed many complex and powerful syscall-based models to serve as anomaly detectors. These models typically show an impressive level of accuracy while emphasizing on minimizing the false positive rate. However, with each proposed model iteration, we get further from the setting in which these models are intended to operate. As kernels become more ornate and hardened, the implementation space for anomaly detection models is narrowing. Furthermore, the rapid advancement of operating systems and the underlying complexity introduced dictate that the sometimes decades-old datasets have long been obsolete. In this paper, we attempt to bridge the gap between theoretical models and their intended application environments by examining the recent Linux kernel 5.7.0-rc1. In this setting, we examine the feasibility of syscall-based HIDS in modern operating systems and the constraints imposed on the HIDS developer. We discuss how recent advancements to the kernel have eliminated the previous syscall trace collect method of writing syscall table wrappers, and propose a new approach to generate data and place our detection model. Furthermore, we present the specific execution time and memory constraints that models must meet in order to be operable within their intended settings. Finally, we conclude with preliminary results from our model, which primarily show that in-kernel machine learning models are feasible, depending on their complexity.

A successful application of an Internet of Things (IoT) based network depends on the accurate and successful delivery of a large amount of data collected from numerous sources. However, the highly dynamic nature of IoT network prevents the establishment of clear security perimeters and hampers the understanding of security aspects. Risk assessment in such networks requires good situational awareness with respect to security. Therefore, a comprehensive view of data propagation including information on security controls can improve security analysis and risk assessment in each layer of data propagation in an IoT architecture. Documentation of metadata is already used in data provenance to identify who generates which data, how, and when. However, documentation of security information is not seen as relevant for data provenance graphs. In this paper, we discuss the importance of adding security metadata in a data provenance graph. We propose a novel IoT Provenance model, Prov-IoT, which documents the history of data records considering data processing and aggregation along with security metadata to enable a foundation for trust in data. The model portrays a comprehensive framework and outlines the identification of information to be included in designing a security-aware provenance graph. This can be beneficial for uncovering system fault or intrusion. Also, it can be useful for decision-based systems for security analysis and risk estimation. We design an associated class diagram for the Prov-IoT model. Finally, we use an IoT healthcare example scenario to demonstrate the impact of the proposed model.

This chapter presents a game‐theoretic model to analyze attack–defense scenarios that use fake nodes (computing devices) for deception under consideration of the system deploying defense resources to protect individual nodes in a cost‐effective manner. The developed model has important applications in the Internet of Battlefield Things (IoBT). Our game‐theoretic model illustrates how the concept of the Nash equilibrium can be used by the defender to intelligently choose which nodes should be used for performing a computation task while deceiving the attacker into expending resources for attacking fake nodes. Our model considers the fact that defense resources may become compromised under an attack and suggests that the defender, in a probabilistic manner, may utilize unprotected nodes for performing a computation while the attacker is deceived into attacking a node with defense resources installed. The chapter also presents a deception‐based strategy to protect a target node that can be accessed via a tree network. Numerical results provide insights into the strategic deception techniques presented in this chapter.

In this paper, we propose a novel deep learning and blockchain-based energy framework for smart grids, entitled DeepCoin. The DeepCoin framework uses two schemes, a blockchain-based scheme and a deep learning-based scheme. The blockchain-based scheme consists of five phases: setup phase, agreement phase, creating a block phase and consensus-making phase, and view change phase. It incorporates a novel reliable peer-to-peer energy system that is based on the practical Byzantine fault tolerance algorithm and it achieves high throughput. In order to prevent smart grid attacks, the proposed framework makes the generation of blocks using short signatures and hash functions. The proposed deep learning-based scheme is an intrusion detection system (IDS), which employs recurrent neural networks for detecting network attacks and fraudulent transactions in the blockchain-based energy network. We study the performance of the proposed IDS on three different sources the CICIDS2017 dataset, a power system dataset, and a web robot (Bot)-Internet of Things (IoT) dataset.

Internet of Things (IoT) has been growing exponentially in the commercial market in recent years. It is also a fact that people hold one or more computing devices at home. Many of them have been developed to operate through internet connectivity with cloud computing technologies that result in the demand for fast, robust, and secure services. In most cases, the lack of these services makes difficult the transfer of data to fulfill the devices' purposes. Under these conditions, an intermediate layer or middleware is needed to process, filter, and send data through a more efficient alternative. This paper presents the adaptive solution of a middleware architecture as an intermediate layer between smart devices and cloud computing to enhance the management of the heterogeneity of data provining from IoT devices. The proposed middleware provides easy configuration, adaptability, and bearability for different environments. Finally, this solution has been implemented in the healthcare domain, in which IoT solutions are deployed into Ambient Assisted Living (AAL) environments.