Biblio

Explainable Artificial Intelligence (XAI) is expected to play a key role in the design phase of next generation cellular networks. As 5G is being implemented and 6G is just in the conceptualization stage, it is increasingly clear that AI will be essential to manage the ever-growing complexity of the network. However, AI models will not only be required to deliver high levels of performance, but also high levels of explainability. In this paper we show how fuzzy models may be well suited to address this challenge. We compare fuzzy and classical decision tree models with a Random Forest (RF) classifier on a Quality of Experience classification dataset. The comparison suggests that, in our setting, fuzzy decision trees are easier to interpret and perform comparably or even better than classical ones in identifying stall events in a video streaming application. The accuracy drop with respect to RF classifier, which is considered to be a black-box ensemble model, is counterbalanced by a significant gain in terms of explainability.

A promising paradigm in protocol design is to hold parties accountable for misbehavior, instead of postulating that they are trustworthy. Recent approaches in defining this property, called accountability, characterized malicious behavior as a deviation from the protocol that causes a violation of the desired security property, but did so under the assumption that all deviating parties are controlled by a single, centralized adversary. In this work, we investigate the setting where multiple parties can deviate with or without coordination in a variant of the applied-π calculus.We first demonstrate that, under realistic assumptions, it is impossible to determine all misbehaving parties; however, we show that accountability can be relaxed to exclude causal dependencies that arise from the behavior of deviating parties, and not from the protocol as specified. We map out the design space for the relaxation, point out protocol classes separating these notions and define conditions under which we can guarantee fairness and completeness. Most importantly, we discover under which circumstances it is correct to consider accountability in the single-adversary setting, where this property can be verified with off-the-shelf protocol verification tools.

Distributed denial of service attacks threaten the security and health of the Internet. Remediation relies on up-to-date and accurate attack signatures. Signature-based detection is relatively inexpensive computationally. Yet, signatures are inflexible when small variations exist in the attack vector. Attackers exploit this rigidity by altering their attacks to bypass the signatures. Our previous work revealed a critical problem with conventional machine learning models. Conventional models are unable to generalize on the temporal nature of network flow data to classify attacks. We thus explored the use of deep learning techniques on real flow data. We found that a variety of attacks could be identified with high accuracy compared to previous approaches. We show that a convolutional neural network can be implemented for this problem that is suitable for large volumes of data while maintaining useful levels of accuracy.

The measurement of room acoustics plays a wide role in audio research, from physical acoustics modelling and virtual reality applications to speech enhancement. While vast literature exists on position-dependent room acoustics and coupling of rooms, little has explored the transition from one room to its neighbour. This paper presents the measurement and analysis of a dataset of spatial room impulse responses for the transition between four coupled room pairs. Each transition consists of 101 impulse responses recorded using a fourth-order spherical microphone array in 5 cm intervals, both with and without a continuous line-of-sight between the source and microphone. A numerical analysis of the room transitions is then presented, including direct-to-reverberant ratio and direction of arrival estimations, along with potential applications and uses of the dataset.

Recently, cyber security in power systems has captured significant interest. This is because the world has seen a surge in cyber attacks on power systems. One of the prolific cyber attacks in modern power systems are False Data Injection Attacks (FDIA). In this paper, we analyzed the impact of FDIA on the operation cost of power systems. Also, we introduced a novel Advanced Persistent Threat (APT) based attack strategy that maximizes the operating costs when attacking specific nodes in the system. We model the attack strategy using an optimization problem and use metaheuristics algorithms to solve the optimization problem and execute the attack. We have found that our attacks can increase the power generation cost by up to 15.6%, 60.12%, and 74.02% on the IEEE 6-Bus systems, 30-Bus systems, and 118-Bus systems, respectively, as compared to normal operation.

To reduce the risk of botnet malware, methods of detecting botnet malware using machine learning have received enormous attention in recent years. Most of the traditional methods are based on supervised learning that relies on static features with defined labels. However, recent studies show that supervised machine learning-based IoT malware botnet models are more vulnerable to intentional attacks, known as an adversarial attack. In this paper, we study the adversarial attack on PSI-graph based researches. To perform the efficient attack, we proposed a reinforcement learning based method with a trained target classifier to modify the structures of PSI-graphs. We show that PSI-graphs are vulnerable to such attack. We also discuss about defense method which uses adversarial training to train a defensive model. Experiment result achieves 94.1% accuracy on the adversarial dataset; thus, shows that our defensive model is much more robust than the previous target classifier.

Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are susceptible to adversarial examples; adversarial examples are well-crafted malicious inputs to the neural network (NN) with the objective to cause erroneous outputs. In this paper, we extend this to regression problems and show that adversarial attacks can break DL-based power allocation in the downlink of a massive multiple-input-multiple-output (maMIMO) network. Specifically, we extend the fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent adversarial attacks in the context of power allocation in a maMIMO system. We benchmark the performance of these attacks and show that with a small perturbation in the input of the NN, the white-box attacks can result in infeasible solutions up to 86%. Furthermore, we investigate the performance of black-box attacks. All the evaluations conducted in this work are based on an open dataset and NN models, which are publicly available.

With the rapid growth of the Internet of Things (IoT) applications in smart regions/cities, for example, smart healthcare, smart homes/offices, there is an increase in security threats and risks. The IoT devices solve real-world problems by providing real-time connections, data and information. Besides this, the attackers can tamper with sensors, add or remove them physically or remotely. In this study, we address the IoT security sensor tampering issue in an office environment. We collect data from real-life settings and apply machine learning to detect sensor tampering using two methods. First, a real-time view of the traffic patterns is considered to train our isolation forest-based unsupervised machine learning method for anomaly detection. Second, based on traffic patterns, labels are created, and the decision tree supervised method is used, within our novel Anomaly Detection using Machine Learning (AD-ML) system. The accuracy of the two proposed models is presented. We found 84% with silhouette metric accuracy of isolation forest. Moreover, the result based on 10 cross-validations for decision trees on the supervised machine learning model returned the highest classification accuracy of 91.62% with the lowest false positive rate.

The fabricated circuitries are getting massive and denser with every passing year due to which a normal automatic test pattern generation technique to detect only the single stuck-at faults will overlook the multiple stuck-at faults. But generating test patterns that can detect all possible multiple stuck-at fault is practically not possible. Hence, this paper proposes a method, where multiple faults can be detected by using test vectors for detecting single stuck-at faults. Here, the patterns for detecting single faults are generated and their ability to detect multiple stuck-at faults is also analyzed. From the experimental results it was observed that, the generated vectors for single faults cover maximum number of the multiple faults and then new test vectors are generated for the undetermined faults. The generated vectors are optimized for the compact test patterns in order to reduce the test power.

In this study, we aim to find a method to autotag sentences specific to a domain. Our training data comprises short conversational sentences extracted from chat conversations between company's customer representatives and web site visitors. We manually tagged approximately 14 thousand visitor inputs into ten basic categories, which will later be used in a transformer-based language model with attention mechanisms for the ultimate goal of developing a chatbot application that can produce meaningful dialogue.We considered three different stateof- the-art models and reported their auto-tagging capabilities. We achieved the best performance with the bidirectional encoder representation from transformers (BERT) model. Implementation of the models used in these experiments can be cloned from our GitHub repository and tested for similar auto-tagging problems without much effort.

In recent years, more and more medical institutions have been using electronic medical records (EMRs) to improve service efficiency and reduce storage cost. However, it is difficult for medical institutions with different management methods to share medical data. The medical data of patients is easy to be abused, and there are security risks of privacy data leakage. The above problems seriously impede the sharing of medical data. To solve these problems, we propose a blockchain-based medical data sharing scheme with attribute-based searchable encryption, named BMDS. In BMDS, encrypted EMRs are securely stored in the interplanetary file system (IPFS), while corresponding indexes and other information are stored in a medical consortium blockchain. The proposed BMDS has the features of tamper-proof, privacy preservation, verifiability and secure key management, and there is no single point of failure. The performance evaluation of computational overhead and security analysis show that the proposed BMDS has more comprehensive security features and practicability.

This paper is concerned with the problem of adaptive finite-time prescribed performance control for a category of uncertain nonlinear systems subject to fuzzy dead-zone input. Via combining the technologies of command filter and backstepping control, the ``singularity'' and the ``explosion of complexity'' issues within controller design procedure are avoided. Moreover, by designing a state observer and utilizing the center-of-gravity theorem, the unmeasured states of system are estimated and the fuzzy issue result from fuzzy dead-zone input is disposed, respectively. Meanwhile, a finite-time fuzzy controller is constructed via combining with finite-time stability criterion, which guarantees all the signals in closed-loop system are convergent and the trajectory of tracking error also strictly evolves within a predefined range in finite time. At last, some simulation results confirm the viability of presented theoretical results.

Reliable group communication is an important cornerstone for various applications in the domain of Industrial Internet of Things (IIoT). Yet, despite various proposals, state-of- the-art (open) protocol stacks for IPv6-enabled Low Power and Lossy Networks (LLNs) have little to offer, regarding standardized or agreed-upon protocols for correct multicast routing, not to mention reliable multicast. We present an informal computational model, which allows us to analyze the respective candidates for multicast routing. Further, we focus on the IEEE 802.15.4/6LoWPAN stack and discuss prominent multicast routing protocols and how they fit into this model.

There is an increasing trend in cloud adoption of enterprise applications in, for example, manufacturing, healthcare, and finance. Such applications are routinely subject to targeted cyberattacks, which result in significant loss of sensitive data (e.g., due to data exfiltration in advanced persistent threats) or valuable utilities (e.g., due to resource the exfiltration of power in cryptojacking). There is a critical need to train highly skilled cybersecurity professionals, who are capable of defending against such targeted attacks. In this article, we present the design, development, and evaluation of the Mizzou Cyber Range, an online platform to learn basic/advanced cyber defense concepts and perform training exercises to engender the next-generation cybersecurity workforce. Mizzou Cyber Range features flexibility, scalability, portability, and extendability in delivering cyberattack/defense learning modules to students. We detail our “research-inspired learning” and “learn-apply-create” three-phase pedagogy methodologies in the development of four learning modules that include laboratory exercises and self-study activities using realistic cloud-based application testbeds. The learning modules allow students to gain skills in using latest technologies (e.g., elastic capacity provisioning, software-defined everything infrastructure) to implement sophisticated “attack defense by pretense” techniques. Students can also use the learning modules to understand the attacker-defender game in order to create disincentives (i.e., pretense initiation) that make the attacker's tasks more difficult, costly, time consuming, and uncertain. Lastly, we show the benefits of our Mizzou Cyber Range through the evaluation of student learning using auto-grading, rank assessments with peer standing, and monitoring of students' performance via feedback from prelab evaluation surveys and postlab technical assessments.

We consider the problem of security for unmanned aerial vehicle flight control systems. To provide a concrete setting, we consider the security problem in the context of a helicopter which is compromised by a malicious agent that distorts elevation measurements to the control loop. This is a particular example of the problem of the security of stochastic control systems under erroneous observation measurements caused by malicious sensors within the system. In order to secure the control system, we consider dynamic watermarking, where a private random excitation signal is superimposed onto the control input of the flight control system. An attack detector at the actuator can then check if the reported sensor measurements are appropriately correlated with the private random excitation signal. This is done via two specific statistical tests whose violation signifies an attack. We apply dynamic watermarking technique to a 2-rotor-based 3-DOF helicopter control system test-bed. We demonstrate through both simulation and experimental results the performance of the attack detector on two attack models: a stealth attack, and a random bias injection attack.

The burgeoning networked computing devices create many distributed systems and generate new signals on a large scale. Many Internet of Things (IoT) applications, such as peer-to-peer streaming of multimedia data, crowdsourcing, and measurement by sensor networks, can be modeled as a form of big data. Processing massive data calls for new data structures and algorithms different from traditional ones designed for small-scale problems. For measurement from networked distributed systems, we consider an essential data format: signals on graphs. Due to limited computing resources, the sensor nodes in the distributed systems may outsource the computing tasks to third parties, such as cloud platforms, arising a severe concern on data privacy. A de-facto solution is to have third parties only process encrypted data. We propose a novel and efficient privacy-preserving secure outsourced computation protocol for denoising signals on the graph based on the information-theoretic secure multi-party computation (ITS-MPC). Denoising the data makes paths for further meaningful data processing. From experimenting with our algorithms in a testbed, the results indicate a better efficiency of our approach than a counterpart approach with computational security.

Cryptography is the science or process used for the encryption and decryption of data that helps the users to store important information or share it across networks where it can be read only by the intended user. In this paper, Elliptic Curve Cryptography (ECC) has been proposed because of its small key size, less memory space and high speed. Elliptic curve scalar multiplication is an important part of elliptic curve systems. Here, the scalar multiplication is performed with the help of hybrid Karatsuba multiplier as the area utilization of Karatsuba multiplier is less. An alternative of digital signature algorithm, that is, Elliptic Curve Digital Signature Algorithm (ECDSA) along with the primary operations of elliptic curves have also been discussed in this paper.

Existing group shilling attack detection methods mainly depend on human feature engineering to extract group attack behavior features, which requires a high knowledge cost. To address this problem, we propose a group shilling attack detection method based on maximum density subtensor mining. First, the rating time series of each item is divided into time windows and the item tensor groups are generated by establishing the user-rating-time window data models of three-dimensional tensor. Second, the M-Zoom model is applied to mine the maximum dense subtensor of each item, and the subtensor groups with high consistency of behaviors are selected as candidate groups. Finally, a dual-input convolutional neural network model is designed to automatically extract features for the classification of real users and group attack users. The experimental results on the Amazon and Netflix datasets show the effectiveness of the proposed method.

In a group shilling attack, attackers work collaboratively to inject fake profiles aiming to obtain desired recommendation result. This type of attacks is more harmful to recommender systems than individual shilling attacks. Previous studies pay much attention to detect individual attackers, and little work has been done on the detection of shilling groups. In this work, we introduce a topic modeling method of natural language processing into shilling attack detection and propose a shilling group detection method on the basis of hierarchical topic model. First, we model the given dataset to a series of user rating documents and use the hierarchical topic model to learn the specific topic distributions of each user from these rating documents to describe user rating behaviors. Second, we divide candidate groups based on rating value and rating time which are not involved in the hierarchical topic model. Lastly, we calculate group suspicious degrees in accordance with several indicators calculated through the analysis of user rating distributions, and use the k-means clustering algorithm to distinguish shilling groups. The experimental results on the Netflix and Amazon datasets show that the proposed approach performs better than baseline methods.

Spatial crowdsourcing has stimulated various new applications such as taxi calling and food delivery. A key enabler for these spatial crowdsourcing based applications is to plan routes for crowd workers to execute tasks given diverse requirements of workers and the spatial crowdsourcing platform. Despite extensive studies on task planning in spatial crowdsourcing, few have accounted for the location privacy of tasks, which may be misused by an untrustworthy platform. In this paper, we explore efficient task planning for workers while protecting the locations of tasks. Specifically, we define the Privacy-Preserving Task Planning (PPTP) problem, which aims at both total revenue maximization of the platform and differential privacy of task locations. We first apply the Laplacian mechanism to protect location privacy, and analyze its impact on the total revenue. Then we propose an effective and efficient task planning algorithm for the PPTP problem. Extensive experiments on both synthetic and real datasets validate the advantages of our algorithm in terms of total revenue and time cost.

The cloud storage system is a very big boon for the organizations and individuals who are all in the need of storage space to accommodate huge volume of digital data. The cloud storage space can handle various types of digital data like text, image, video and audio. Since the storage space can be shared among different users, it is possible to have duplicate copies of data in the storage space. An efficient mechanism is required to identify the digital data uniquely in order to check the duplicity. There are various ways by which the digital data can be identified. One among such technique is hash-based identification. Using cryptographic hashing algorithms, every data can be uniquely identified. The unique property of hashing algorithm helps to identify the data uniquely. In this research work, we are going to discuss the advantage of using cryptographic hashing algorithm for digital data identification and the comparison of various hashing algorithms.

In recent times, security and privacy concerns associated with IoT devices have caught the attention of research community. The problem of securing IoT devices is immensely aggravating due to advancement in technology. These IoT devices are resource-constraint i.e. in terms of power, memory, computation, etc., so they are less capable to secure themselves. So we need a better approach to secure IoT devices within the limited resources. Several studies state that for these lightweight IoT devices Elliptic Curve Cryptography (ECC) suits perfectly. But there are several elliptic curve domain parameter standards, which may be used for different security levels. When any ECC based product is deployed then the selection of a suitable elliptic curve standard according to usability is become very important. So we have to choose one suitable standard domain parameter for the required security level. In this paper, two different elliptic curve standard domain parameters named secp256k1 and secp192k1 proposed by an industry consortium named Standards for Efficient Cryptography Group (SECG) [1] are implemented and then analyzed their performances metrics. The performance of each domain parameter is measured in computation time.

This work studies an energy-efficient jamming scheme for enhancing physical layer security in visible light communication (VLC). We consider a VLC system where multiple LED luminaries are deployed together with a legitimate user (i.e., Bob) and passive eavesdroppers (i.e., Eves). In such a scenario, the closest LED luminary to Bob serves as the transmitter while the rest of the luminaries act as jammers transmitting artificial noise (AN) to possibly degrade the quality of Eves' channels. A joint design of precoder and AN is then investigated to maximize the energy efficiency (EE) of the communication channel to Bob while ensuring a certain amount of AN power to confuse Eves. To solve the design problem, we make use of a combination of the Dinkelbach and convex-concave procedure (CCCP), which guarantees to converge to a local optimum.

In this paper, the adaptive event-triggered asymptotic tracking control with guaranteed performance for a single link robot manipulator (SLRM) system driven by the brush DC motor is studied. Fuzzy logic systems (FLS) is used to approximate unknown nonlinear functions. By introducing a finite time performance function (FTPF), the tracking error of the system can converge to the compact set of the origin in finite time. In addition, by introducing the smooth function and some positive integral functions, combined with the boundary estimation method and adaptive backstepping technique, the asymptotic tracking control of the system is realized. Meanwhile, event-triggered mechanism is introduced to reduce the network resources of the system. Finally, a practical example is given to prove the effectiveness of the theoretical research.

In view of the problem that the convolution neural network research of facial expression recognition ignores the internal relevance of the key links, which leads to the low accuracy and speed of facial expression recognition, and can't meet the recognition requirements, a series cascade algorithm model for expression recognition of educational robot is constructed and enables the educational robot to recognize multiple students' facial expressions simultaneously, quickly and accurately in the process of movement, in the balance of the accuracy, rapidity and stability of the algorithm, based on the cascade convolution neural network model. Through the CK+ and Oulu-CASIA expression recognition database, the expression recognition experiments of this algorithm are compared with the commonly used STM-ExpLet and FN2EN cascade network algorithms. The results show that the accuracy of the expression recognition method is more than 90%. Compared with the other two commonly used cascade convolution neural network methods, the accuracy of expression recognition is significantly improved.