With the recent advancements in automated communication technology, many traditional businesses that rely on face-to-face communication have shifted to online portals. However, these online platforms often lack the personal touch essential for customer service. Research has shown that face-to- face communication is essential for building trust and empathy with customers. A multimodal embodied conversation agent (ECA) can fill this void in commercial applications. Such a platform provides tools to understand the user’s mental state by analyzing their verbal and non-verbal behaviour and allows a human-like avatar to take necessary action based on the context of the conversation and as per social norms. However, the literature to understand the impact of ECA agents on commercial applications is limited because of the issues related to platform and scalability. In our work, we discuss some existing work that tries to solve the issues related to scalability and infrastructure. We also provide an overview of the components required for developing ECAs and their deployment in various applications.

With the rapid development of artificial intelligence (AI), many companies are moving towards automating their services using automated conversational agents. Dialogue-based conversational recommender agents, in particular, have gained much attention recently. The successful development of such systems in the case of natural language input is conditioned by the ability to understand the users’ utterances. Predicting the users’ intents allows the system to adjust its dialogue strategy and gradually upgrade its preference profile. Nevertheless, little work has investigated this problem so far. This paper proposes an LSTM-based Neural Network model and compares its performance to seven baseline Machine Learning (ML) classifiers. Experiments on a new publicly available dataset revealed The superiority of the LSTM model with 95% Accuracy and 94% F1-score on the full dataset despite the relatively small dataset size (9300 messages and 17 intents) and label imbalance.

Recent advances in deep learning typically, with the introduction of transformer based models has shown massive improvement and success in many Natural Language Processing (NLP) tasks. One such area which has leveraged immensely is conversational agents or chatbots in open-ended (chit-chat conversations) and task-specific (such as medical or legal dialogue bots etc.) domains. However, in the era of automation, there is still a dearth of works focused on one of the most relevant use cases, i.e., tutoring dialog systems that can help students learn new subjects or topics of their interest. Most of the previous works in this domain are either rule based systems which require a lot of manual efforts or are based on multiple choice type factual questions. In this paper, we propose EDICA (Educational Domain Infused Conversational Agent), a language tutoring Virtual Agent (VA). EDICA employs two mechanisms in order to converse fluently with a student/user over a question and assist them to learn a language: (i) Student/Tutor Intent Classification (SIC-TIC) framework to identify the intent of the student and decide the action of the VA, respectively, in the on-going conversation and (ii) Tutor Response Generation (TRG) framework to generate domain infused and intent/action conditioned tutor responses at every step of the conversation. The VA is able to provide hints, ask questions and correct student's reply by generating an appropriate, informative and relevant tutor response. We establish the superiority of our proposed approach on various evaluation metrics over other baselines and state of the art models.

Populations move across regions in search of better living possibilities, better life outcomes or going away from problems that affected their lives in the previous region they lived in. In the United States of America, this problem has been happening over decades. Intelligent Conversational Text-based Agents, also called Chatbots, and Artificial Intelligence are increasingly present in our lives and over recent years, their presence has increased considerably, due to the usability cases and the familiarity they are wining constantly. Using NLP algorithms for law in accessible platforms allows scaling of users to access a certain level of law expert who could assist users in need. This paper describes the motivation and circumstances of this problem as well as the description of the development of an Intelligent Conversational Agent system that was used by immigrants in the USA so they could get answers to questions and get suggestions about better legal options they could have access to. This system has helped thousands of people, especially in California

Due to the migration megatrend, efficient and effective second-language acquisition is vital. One proposed solution involves AI-enabled conversational agents for person-centered interactive language practice. We present results from ongoing action research targeting quality assurance of proprietary generative dialog models trained for virtual job interviews. The action team elicited a set of 38 requirements for which we designed corresponding automated test cases for 15 of particular interest to the evolving solution. Our results show that six of the test case designs can detect meaningful differences between candidate models. While quality assurance of natural language processing applications is complex, we provide initial steps toward an automated framework for machine learning model selection in the context of an evolving conversational agent. Future work will focus on model selection in an MLOps setting.

In this work, the use of an undercover conversational agent, acting as a participative student in a synchronous virtual reality distance learning scenario is proposed to stimulate social interaction between teacher and students. The outcome of an exploratory user study indicated that the undercover conversational agent is capable of fostering interaction, relieving social pressure, and overall leading to a more satisfactory and engaging learning experience without sacrificing learning performance.

In recent years, business environments are undergoing disruptive changes across sectors [1]. Globalization and technological advances, such as artificial intelligence and the internet of things, have completely redesigned business activities, bringing to light an ever-increasing interest and attention towards the customer [2], especially in healthcare sector. In this context, researchers is paying more and more attention to the introduction of new technologies capable of meeting the patients’ needs [3, 4] and the Covid-19 pandemic has contributed and still contributes to accelerate this phenomenon [5]. Therefore, emerging technologies (i.e., AI-enabled solutions, service robots, conversational agents) are proving to be effective partners in improving medical care and quality of life [6]. Conversational agents, often identified in other ways as “chatbots”, are AI-enabled service robots based on the use of text [7] and capable of interpreting natural language and ensuring automation of responses by emulating human behavior [8, 9, 10]. Their introduction is linked to help institutions and doctors in the management of their patients [11, 12], at the same time maintaining the negligible incremental costs thanks to their virtual aspect [13–14]. However, while the utilization of these tools has significantly increased during the pandemic [15, 16, 17], it is unclear what benefits they bring to service delivery. In order to identify their contributions, there is a need to find out which activities can be supported by conversational agents.This paper takes a grounded approach [18] to achieve contextual understanding design and to effectively interpret the context and meanings related to conversational agents in healthcare interactions. The study context concerns six chatbots adopted in the healthcare sector through semi-structured interviews conducted in the health ecosystem. Secondary data relating to these tools under consideration are also used to complete the picture on them. Observation, interviewing and archival documents [19] could be used in qualitative research to make comparisons and obtain enriched results due to the opportunity to bridge the weaknesses of one source by compensating it with the strengths of others. Conversational agents automate customer interactions with smart meaningful interactions powered by Artificial Intelligence, making support, information provision and contextual understanding scalable. They help doctors to conduct the conversations that matter with their patients. In this context, conversational agents play a critical role in making relevant healthcare information accessible to the right stakeholders at the right time, defining an ever-present accessible solution for patients’ needs. In summary, conversational agents cannot replace the role of doctors but help them to manage patients. By conveying constant presence and fast information, they help doctors to build close relationships and trust with patients.

Intelligent Virtual Agents (IVAs) have become ubiquitous in our daily lives, displaying increased complexity of form and function. Initial IVA development efforts provided basic functionality to suit users' needs, typically in work or educational settings, but are now present in numerous contexts in more realistic, complex forms. In this paper, we focus on personalization of embodied human intelligent virtual agents to assist individuals as part of physical training “exergames”.

Over the past two decades, several forms of non-intrusive technology have been deployed in cooperation with medical specialists in order to aid patients diagnosed with some form of mental, cognitive or psychological condition. Along with the availability and accessibility to applications offered by mobile devices, as well as the advancements in the field of Artificial Intelligence applications and Natural Language Processing, Conversational Agents have been developed with the objective of aiding medical specialists detecting those conditions in their early stages and monitoring their symptoms and effects on the cognitive state of the patient, as well as supporting the patient in their effort of mitigating those symptoms. Coupled with the recent advances in the the scientific field of machine and deep learning, we aim to explore the grade of applicability of such technologies into cognitive health support Conversational Agents, and their impact on the acceptability of such applications bytheir end users. Therefore, we conduct a systematic literature review, following a transparent and thorough process in order to search and analyze the bibliography of the past five years, focused on the implementation of Conversational Agents, supported by Artificial Intelligence technologies and in service of patients diagnosed with Mild Cognitive Impairment and its variants.

Conversational Intelligent Tutoring Systems (CITS) in learning environments are capable of providing personalized instruction to students in different domains, to improve the learning process. This interaction between the Intelligent Tutoring System (ITS) and the user is carried out through dialogues in natural language. In this study, we use an open source framework called Rasa to adapt the original button-based user interface of an algebraic/arithmetic word problem-solving ITS to one based primarily on the use of natural language. We conducted an empirical study showing that once properly trained, our conversational agent was able to recognize the intent related to the content of the student’s message with an average accuracy above 0.95.

The emergence of smart cars has revolutionized the automotive industry. Today's vehicles are equipped with different types of electronic control units (ECUs) that enable autonomous functionalities like self-driving, self-parking, lane keeping, and collision avoidance. The ECUs are connected to each other through an in-vehicle network, named Controller Area Network. In this talk, we will present the different cyber attacks that target autonomous vehicles and explain how an intrusion detection system (IDS) using machine learning can play a role in securing the Controller Area Network. We will also discuss the main research contributions for the security of autonomous vehicles. Specifically, we will describe our IDS, named Histogram-based Intrusion Detection and Filtering framework. Next, we will talk about the machine learning explainability issue that limits the acceptability of machine learning in autonomous vehicles, and how it can be addressed using our novel intrusion detection system based on rule extraction methods from Deep Neural Networks.

Nowadays, safety systems are an important feature for modern vehicles. Many accidents would have been occurred without them. In comparison with older vehicles, modern vehicles have a much better crumple zone, more airbags, a better braking system, as well as a much better and safer driving behaviour. Although, the vehicles safety systems are working well in these days, there is still space for improvement and for adding new security features. This paper describes the implementation of an Intelligent Caravan Monitoring System (ICMS) using the Controller Area Network (CAN), for the communication between the vehicle’s electronic system and the trailer’s electronic system. Furthermore, a comparison between the communication technology of this paper and a previous published paper will be made. The new system is faster, more flexible and more energy efficient.

International regulations specified in WP.29 and international standards specified in ISO/SAE 21434 require security operations such as cyberattack detection and incident responses to protect vehicles from cyberattacks. To meet these requirements, many vehicle manufacturers are planning to install Intrusion Detection Systems (IDSs) in the Controller Area Network (CAN), which is a primary component of in-vehicle networks, in the coming years. Besides, many vehicle manufacturers and information security companies are developing technologies to identify attack paths related to IDS alerts to respond to cyberattacks appropriately and quickly. To develop the IDSs and the technologies to identify attack paths, it is essential to grasp normal communications performed on in-vehicle networks. Thus, our study aims to develop a technology that can easily grasp normal communications performed on in-vehicle networks. In this paper, we propose the first message source identification method that easily identifies CAN-IDs used by each Electronic Control Unit (ECU) connected to the CAN for message transmissions. We realize the proposed method by utilizing diagnostic communications and an IDS installed in the CAN (CAN-IDS). We evaluate the proposed method using an ECU installed in an actual vehicle and four kinds of simulated CAN-IDSs based on typical existing intrusion detection methods for the CAN. The evaluation results show that the proposed method can identify the CAN-ID used by the ECU for CAN message transmissions if a suitable simulated CAN-IDS for the proposed method is connected to the vehicle.

Modern connected vehicles are equipped with a large number of sensors, which enable a wide range of services that can improve overall traffic safety and efficiency. However, remote access to connected vehicles also introduces new security issues affecting both inter and intra-vehicle communications. In fact, existing intra-vehicle communication systems, such as Controller Area Network (CAN), lack security features, such as encryption and secure authentication for Electronic Control Units (ECUs). Instead, Original Equipment Manufacturers (OEMs) seek security through obscurity by keeping secret the proprietary format with which they encode the information. Recently, it has been shown that the reuse of CAN frame IDs can be exploited to perform CAN bus reverse engineering without physical access to the vehicle, thus raising further security concerns in a connected environment. This work investigates whether anonymizing the frames of each newly released vehicle is sufficient to prevent CAN bus reverse engineering based on frame ID matching. The results show that, by adopting Machine Learning techniques, anonymized CAN frames can still be fingerprinted and identified in an unknown vehicle with an accuracy of up to 80 %.

Intrusion detection for Controller Area Network (CAN) protocol requires modern methods in order to compete with other electrical architectures. Fingerprint Intrusion Detection Systems (IDS) provide a promising new approach to solve this problem. By characterizing network traffic from known ECUs, hazardous messages can be discriminated. In this article, a modified version of Fingerprint IDS is employed utilizing both step response and spectral characterization of network traffic via neural network training. With the addition of feature set reduction and hyperparameter tuning, this method accomplishes a 99.4% detection rate of trusted ECU traffic.

Present-day vehicles have numerous Electronic Control Units (ECUs) and they communicate with each other over a network known as the Controller Area Network(CAN) bus. In this way, the CAN bus is a fundamental component of intra-vehicle communication. The CAN bus was designed without focusing on communication security and in this way it is vulnerable to many cyber attacks. As the vehicles are always connected to the Internet, the CAN bus is remotely accessible and could be hacked. To secure the communication between ECUs and defend against these cyber attacks, we apply a Hash Message Authentication Code(HMAC) to automotive data and demonstrate the CAN bus communication between two ECUs using Arduino UNO and MCP2515 CAN bus module.

This paper presents a case study for designing and implementing a secure communication protocol over a Controller Area Network (CAN). The CAN based protocol uses a hybrid encryption method on a relatively simple hardware / software environment. Moreover, the blockchain technology is proposed as a working solution to provide an extra secure level of the proposed system.

In construction machinery, connectivity delivers higher advantages in terms of higher productivity, lower costs, and most importantly safer work environment. As the machinery grows more dependent on internet-connected technologies, data security and product cybersecurity become more critical than ever. These machines have more cyber risks compared to other automotive segments since there are more complexities in software, larger after-market options, use more standardized SAE J1939 protocol, and connectivity through long-distance wireless communication channels (LTE interfaces for fleet management systems). Construction machinery also operates throughout the day, which means connected and monitored endlessly. Till today, construction machinery manufacturers are investigating the product cybersecurity challenges in threat monitoring, security testing, and establishing security governance and policies. There are limited security testing methodologies on SAE J1939 CAN protocols. There are several testing frameworks proposed for fuzz testing CAN networks according to [1]. This paper proposes security testing methods (Fuzzing, Pen testing) for in-vehicle communication protocols in construction machinery.

Controller Area Network with Flexible Data-rate(CAN FD) has the advantages of high bandwidth and data field length to meet the higher communication requirements of parallel in-vehicle applications. If the CAN FD lacking the authentication security mechanism is used, it is easy to make it suffer from masquerade attack. Therefore, a two-stage method based on message authentication is proposed to enhance the security of it. In the first stage, an anti-exhaustive message exchange and comparison algorithm is proposed. After exchanging the message comparison sequence, the lower bound of the vehicle application and redundant message space is obtained. In the second stage, an enhanced round accumulation algorithm is proposed to enhance security, which adds Message Authentication Codes(MACs) to the redundant message space in a way of fewer accumulation rounds. Experimental examples show that the proposed two-stage approach enables both small-scale and large-scale parallel in-vehicle applications security to be enhanced. Among them, in the Adaptive Cruise Control Application(ACCA), when the laxity interval is 1300μs, the total increased MACs is as high as 388Bit, and the accumulation rounds is as low as 40 rounds.

The Controller area network (CAN) is the most extensively used in-vehicle network. It is set to enable communication between a number of electronic control units (ECU) that are widely found in most modern vehicles. CAN is the de facto in-vehicle network standard due to its error avoidance techniques and similar features, but it is vulnerable to various attacks. In this research, we propose a CAN bus intrusion detection system (IDS) based on convolutional neural networks (CNN). U-CAN is a segmentation model that is trained by monitoring CAN traffic data that are preprocessed using hamming distance and saliency detection algorithm. The model is trained and tested using publicly available datasets of raw and reverse-engineered CAN frames. With an F\_1 Score of 0.997, U-CAN can detect DoS, Fuzzy, spoofing gear, and spoofing RPM attacks of the publicly available raw CAN frames. The model trained on reverse-engineered CAN signals that contain plateau attacks also results in a true positive rate and false-positive rate of 0.971 and 0.998, respectively.

In this work, the security sliding mode control issue is studied for interval type-2 (IT2) fuzzy systems under the unreliable network. The deception attacks and the denial-of-service (DoS) attacks may occur in the sensor-controller channels to affect the transmission of the system state, and these attacks are described via two independent Bernoulli stochastic variables. By adopting the compensation strategy and utilizing the available state, the new membership functions are constructed to design the fuzzy controller with the different fuzzy rules from the fuzzy model. Then, under the mismatched membership function, the designed security controller can render the closed-loop IT2 fuzzy system to be stochastically stable and the sliding surface to be reachable. Finally, the simulation results verify the security control scheme.

We investigate the fuzzy adaptive compensation control problem for nonlinear cyber-physical system with false data injection attack over digital communication links. The fuzzy logic system is first introduced to approximate uncertain nonlinear functions. And the time-varying sliding mode surface is designed. Secondly, for the actual require-ment of data transmission, three uniform quantizers are designed to quantify system state and sliding mode surface and control input signal, respectively. Then, the adaptive fuzzy laws are designed, which can effectively compensate for FDI attack and the quantization errors. Furthermore, the system stability and the reachability of sliding surface are strictly guaranteed by using adaptive fuzzy laws. Finally, we use an example to verify the effectiveness of the method.

The paper aims to discover vulnerabilities by application of supervisory control theory and to design a defensive supervisor against vulnerability attacks. Supervisory control restricts the system behavior to satisfy the control specifications. The existence condition of the supervisor, sometimes results in undesirable plant behavior, which can be regarded as a vulnerability of the control specifications. We aim to design a more robust supervisor against this vulnerability.

With the high-speed development of UHV power grid, the characteristics of power grid changed significantly, which puts forward new requirements for the safe operation of power grid and depend on Security and Stability Control System (SSCS) greatly. Based on the practical cases, this paper analyzes the principle of the abnormal criteria of the SSCS and its influence on the strategy of the SSCS, points out the necessity of the research on the locking strategy of the SSCS under the abnormal state. Taking the large-scale SSCS for an example, this paper analysis different control strategies of the stations in the different layered, and puts forward effective solutions to adapt different system functions. It greatly improved the effectiveness and reliability of the strategy of SSCS, and ensure the integrity of the system function. Comparing the different schemes, the principles of making the lock-strategy are proposed. It has reference significance for the design, development and implementation of large-scale SSCS.

Cyber-Physical Systems (CPSs), a class of complex intelligent systems, are considered the backbone of Industry 4.0. They aim to achieve large-scale, networked control of dynamical systems and processes such as electricity and gas distribution networks and deliver pervasive information services by combining state-of-the-art computing, communication, and control technologies. However, CPSs are often highly nonlinear and uncertain, and their intrinsic reliance on open communication platforms increases their vulnerability to security threats, which entails additional challenges to conventional control design approaches. Indeed, sensor measurements and control command signals, whose integrity plays a critical role in correct controller design, may be interrupted or falsely modified when broadcasted on wireless communication channels due to cyber attacks. This can have a catastrophic impact on CPS performance. In this paper, we first conduct a thorough analysis of recently developed secure and resilient control approaches leveraging the solid foundations of adaptive control theory to achieve security and resilience in networked CPSs against sensor and actuator attacks. Then, we discuss the limitations of current adaptive control strategies and present several future research directions in this field.