Biblio

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explain aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.

The rapid shift towards smart cities, particularly in the era of pandemics, necessitates the employment of e-learning, remote learning systems, and hybrid models. Building adaptive and personalized education becomes a requirement to mitigate the downsides of distant learning while maintaining high levels of achievement. Explainable artificial intelligence (XAI), machine learning (ML), and the internet of behaviour (IoB) are just a few of the technologies that are helping to shape the future of smart education in the age of smart cities through Customization and personalization. This study presents a paradigm for smart education based on the integration of XAI and IoB technologies. The research uses data acquired on students' behaviours to determine whether or not the current education systems respond appropriately to learners' requirements. Despite the existence of sophisticated education systems, they have not yet reached the degree of development that allows them to be tailored to learners' cognitive needs and support them in the absence of face-to-face instruction. The study collected data on 41 learner's behaviours in response to academic activities and assessed whether the running systems were able to capture such behaviours and respond appropriately or not; the study used evaluation methods that demonstrated that there is a change in students' academic progression concerning monitoring using IoT/IoB to enable a relative response to support their progression.

This work proposed a unified approach to increase the explainability of the predictions made by Convolution Neural Networks (CNNs) on medical images using currently available Explainable Artificial Intelligent (XAI) techniques. This method in-cooperates multiple techniques such as LISA aka Local Interpretable Model Agnostic Explanations (LIME), integrated gradients, Anchors and Shapley Additive Explanations (SHAP) which is Shapley values-based approach to provide explanations for the predictions provided by Blackbox models. This unified method increases the confidence in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists. In this work, a Chest X-ray (CXR) classification model for identifying Covid-19 patients is trained using transfer learning to illustrate the applicability of XAI techniques and the unified method (LISA) to explain model predictions. To derive predictions, an image-net based Inception V2 model is utilized as the transfer learning model.

Electrical load forecasting is an essential part of the smart grid to maintain a stable and reliable grid along with helping decisions for economic planning. With the integration of more renewable energy resources, especially solar photovoltaic (PV), and transitioning into a prosumer-based grid, electrical load forecasting is deemed to play a crucial role on both regional and household levels. However, most of the existing forecasting methods can be considered black-box models due to deep digitalization enablers, such as Deep Neural Networks (DNN), where human interpretation remains limited. Additionally, the black box character of many models limits insights and applicability. In order to mitigate this shortcoming, eXplainable Artificial Intelligence (XAI) is introduced as a measure to get transparency into the model’s behavior and human interpretation. By utilizing XAI, experienced power market and system professionals can be integrated into developing the data-driven approach, even without knowing the data science domain. In this study, an electrical load forecasting model utilizing an XAI tool for a Norwegian residential building was developed and presented.

In order to solve the problems that may arise from the negative impact of EV charging loads on the power distribution network, it is very important to predict the distribution network variability according to EV charging loads. If appropriate facility reinforcement or system operation is made through evaluation of the impact of EV charging load, it will be possible to prevent facility failure in advance and maintain the power quality at a certain level, enabling stable network operation. By analysing the degree of change in the predicted load according to the EV load characteristics through the load prediction model, it is possible to evaluate the influence of the distribution network according to the EV linkage. This paper aims to investigate the effect of EV charging load on voltage stability, power loss, reliability index and economic loss of distribution network. For this, we transformed univariate time series of EV charging data into a multivariate time series using feature engineering techniques. Then, time series forecast models are trained based on the multivariate dataset. Finally, XAI techniques such as LIME and SHAP are applied to the models to obtain the feature importance analysis results.

Many studies have been conducted to detect various malicious activities in cyberspace using classifiers built by machine learning. However, it is natural for any classifier to make mistakes, and hence, human verification is necessary. One method to address this issue is eXplainable AI (XAI), which provides a reason for the classification result. However, when the number of classification results to be verified is large, it is not realistic to check the output of the XAI for all cases. In addition, it is sometimes difficult to interpret the output of XAI. In this study, we propose a machine learning model called classification verifier that verifies the classification results by using the output of XAI as a feature and raises objections when there is doubt about the reliability of the classification results. The results of experiments on malicious website detection and malware detection show that the proposed classification verifier can efficiently identify misclassified malicious activities.

The growing complexity of wireless networks has sparked an upsurge in the use of artificial intelligence (AI) within the telecommunication industry in recent years. In network slicing, a key component of 5G that enables network operators to lease their resources to third-party tenants, AI models may be employed in complex tasks, such as short-term resource reservation (STRR). When AI is used to make complex resource management decisions with financial and service quality implications, it is important that these decisions be understood by a human-in-the-loop. In this paper, we apply state-of-the-art techniques from the field of Explainable AI (XAI) to the problem of STRR. Using real-world data to develop an AI model for STRR, we demonstrate how our XAI methodology can be used to explain the real-time decisions of the model, to reveal trends about the model’s general behaviour, as well as aid in the diagnosis of potential faults during the model’s development. In addition, we quantitatively validate the faithfulness of the explanations across an extensive range of XAI metrics to ensure they remain trustworthy and actionable.

The number of publications related to Explainable Artificial Intelligence (XAI) has increased rapidly this last decade. However, the subjective nature of explainability has led to a lack of consensus regarding commonly used definitions for explainability and with differing problem statements falling under the XAI label resulting in a lack of comparisons. This paper proposes in broad terms a simple comparison framework for XAI methods based on the output and what we call the practical attributes. The aim of the framework is to ensure that everything that can be held constant for the purpose of comparison, is held constant and to ignore many of the subjective elements present in the area of XAI. An example utilizing such a comparison along the lines of the proposed framework is performed on local, post-hoc, model-agnostic XAI algorithms which are designed to measure the feature importance/contribution for a queried instance. These algorithms are assessed on two criteria using synthetic datasets across a range of classifiers. The first is based on selecting features which contribute to the underlying data structure and the second is how accurately the algorithms select the features used in a decision tree path. The results from the first comparison showed that when the classifier was able to pick up the underlying pattern in the model, the LIME algorithm was the most accurate at selecting the underlying ground truth features. The second test returned mixed results with some instances in which the XAI algorithms were able to accurately return the features used to produce predictions, however this result was not consistent.

Certificate Authorities (CAs) are important components for digital certificate issuances in Public Key Infrastructure(PKI). However, current CAs have some intrinsic weaknesses due to the CA-centric implementation. And when browser and operating system vendors contain a CA in the software, they place complete trust in the CA. In this paper, we utilize natural characteristics of tamper-proof and transparency of smart contracts in blockchain platforms to design an independent entity, named the CA proxy, to manage life cycle of digital certificates. This management will achieve the certificate transparency. We propose a new system architecture easy to integrate the CA proxy with current CAs through applying the blockchain oracle service. In this architecture, the CA proxy, CAs, and even professional identity verification parties can accomplish life cycle management of certificates, signature of certificates, identity verification for certificates correspondingly. The achievement of the certificate transparency through life cycle management of digital certificates in blockchain platforms, when compared with traditional CAs, solves traditional CAs' trust model weaknesses and improve the security.

Peer-to-peer (P2P) systems such as BitTorrent and Bitcoin are susceptible to serious attacks from byzantine nodes that join as peers. Due to well-known impossibility results for designing P2P primitives in unrestricted byzantine settings, research has explored many adversarial models with additional assumptions, ranging from mild (such as pre-established PKI) to strong (such as the existence of common random coins). One such widely-studied model is the general-omission model, which yields simple protocols with good efficiency, but has been considered impractical or unrealizable since it artificially limits the adversary only to omitting messages.In this work, we study the setting of a synchronous network wherein peer nodes have CPUs equipped with a recent trusted computing mechanism called Intel SGX. In this model, we observe that the byzantine adversary reduces to the adversary in the general-omission model. As a first result, we show that by leveraging SGX features, we eliminate any source of advantage for a byzantine adversary beyond that gained by omitting messages, making the general-omission model realizable. Our evaluation of 1000 nodes running on 40 DeterLab machines confirms theoretical efficiency claim.

The industrial Internet has built a new industrial manufacturing and service system with all elements, all industrial chains and all value chains connected through the interconnection of people, machines and things. It breaks the relatively closed and credible production environment of traditional industry. But at the same time, the full interconnection of cross-device, cross-system, and cross-region in the industrial Internet also brings a certain network trust crisis. The method proposed in this paper breaking the relatively closed manufacturing environment of traditional industries, extends the network connection object from human to machine equipment, industrial products and industrial services. It provides a safe and credible environment for the development of industrial Internet, and a trust guarantee for the across enterprises entities and data sharing.

Objective measures are ubiquitous in the formulation, design and implementation of deep space missions. Tour durations, flyby altitudes, propellant budgets, power consumption, and other metrics are essential to developing and managing NASA missions. But beyond the simple metrics of cost and workforce, it has been difficult to identify objective, quantitative measures that assist in evaluating choices made during formulation or implementation phases in terms of their impact on flight operations. As part of the development of the Europa Clipper Mission system, a set of operations metrics have been defined along with the necessary design information and software tooling to calculate them. We have applied these methods and metrics to help assess the impact to the flight team on the six options for the Clipper Tour that are currently being vetted for selection in the fall of 2021. To generate these metrics, the Clipper MOS team first designed the set of essential processes by which flight operations will be conducted, using a standard approach and template to identify (among other aspects) timelines for each process, along with their time constraints (e.g., uplinks for sequence execution). Each of the resulting 50 processes is documented in a common format and concurred by stakeholders. Process timelines were converted into generic schedules and workforce-loaded using COTS scheduling software, based on the inputs of the process authors and domain experts. Custom code was generated to create an operations schedule for a specific portion of Clipper's prime mission, with instances of a given process scheduled based on specific timing rules (e.g., process X starts once per week on Thursdays) or relative to mission events (e.g., sequence generation process begins on a Monday, at least three weeks before each Europa closest approach). Over a 5-month period, and for each of six Clipper candidate tours, the result was a 20,000+ line, workforce-loaded schedule that documents all of the process-driven work effort at the level of individual roles, along with a significant portion of the level-of-effort work. Post-processing code calculated the absolute and relative number of work hours during a nominal 5 day / 40 hour work week, the work effort during 2nd and 3rd shift, as well as 1st shift on weekends. The resultant schedules and shift tables were used to generate objective measures that can be related to both human factors and to operational risk and showed that Clipper tours which utilize 6:1 resonant (21.25 day) orbits instead of 4:1 resonant (14.17 day) orbits during the first dozen or so Europa flybys are advantageous to flight operations. A similar approach can be extended to assist missions in more objective assessments of a number of mission issues and trades, including tour selection and spacecraft design for operability.

With the objective to eliminate the input current sensor in a totem-pole boost power factor corrector (PFC) for its low-cost design, a novel discretized sampling-based robust control scheme is proposed in this work. The proposed control methodology proves to be beneficial due to its ease of implementation and its ability to support high-frequency operation, while being able to eliminate one sensor and, thus, enhancing reliability and cost-effectiveness. In addition, detailed closed-loop stability analysis is carried out for the controller in discrete domain to ascertain brisk dynamic operation when subjected to sudden load fluctuations. To establish the robustness of the proposed control scheme, a detailed sensitivity analysis of the closed-loop performance metrics with respect to undesired changes and inherent uncertainty in system parameters is presented in this article. A comparison with the state-of-the-art (SOA) methods is provided, and conclusive results in terms of better dynamic performance are also established. To verify and elaborate on the specifics of the proposed scheme, a detailed simulation study is conducted, and the results show 25% reduction in response time as compared to SOA approaches. A 500-W boost PFC prototype is developed and tested with the proposed control scheme to evaluate and benchmark the system steady-state and dynamic performance. A total harmonic distortion of 1.68% is obtained at the rated load with a resultant power factor of 0.998 (lag), which proves the effectiveness and superiority of the proposed control scheme.

With the increasing number of catastrophic weather events and resulting disruption in the energy supply to essential loads, the distribution grid operators’ focus has shifted from reliability to resiliency against high impact, low-frequency events. Given the enhanced automation to enable the smarter grid, there are several assets/resources at the disposal of electric utilities to enhances resiliency. However, with a lack of comprehensive resilience tools for informed operational decisions and planning, utilities face a challenge in investing and prioritizing operational control actions for resiliency. The distribution system resilience is also highly dependent on system attributes, including network, control, generating resources, location of loads and resources, as well as the progression of an extreme event. In this work, we present a novel multi-stage resilience measure called the Anticipate-Withstand-Recover (AWR) metrics. The AWR metrics are based on integrating relevant ‘system characteristics based factors’, before, during, and after the extreme event. The developed methodology utilizes a pragmatic and flexible approach by adopting concepts from the national emergency preparedness paradigm, proactive and reactive controls of grid assets, graph theory with system and component constraints, and multi-criteria decision-making process. The proposed metrics are applied to provide decision support for a) the operational resilience and b) planning investments, and validated for a real system in Alaska during the entirety of the event progression.

Recent approaches have proven the effectiveness of local outlier factor-based outlier detection when applied over traffic flow probability distributions. However, these approaches used distance metrics based on the Bhattacharyya coefficient when calculating probability distribution similarity. Consequently, the limited expressiveness of the Bhattacharyya coefficient restricted the accuracy of the methods. The crucial deficiency of the Bhattacharyya distance metric is its inability to compare distributions with non-overlapping sample spaces over the domain of natural numbers. Traffic flow intensity varies greatly, which results in numerous non-overlapping sample spaces, rendering metrics based on the Bhattacharyya coefficient inappropriate. In this work, we address this issue by exploring alternative distance metrics and showing their applicability in a massive real-life traffic flow data set from 26 vital intersections in The Hague. The results on these data collected from 272 sensors for more than two years show various advantages of the Earth Mover's distance both in effectiveness and efficiency.

Flexibility and speed in the development of new industrial machines are essential factors for the success of capital goods industries. When assembling a printed circuit board (PCB), since all the components are surface mounted devices (SMD), the whole process is automatic. However, in many PCBs, it is necessary to place components that are not SMDs, called pin through hole components (PTH), having to be inserted manually, which leads to delays in the production line. This work proposes and validates a prototype work cell based on a collaborative robot and vision systems whose objective is to insert these components in a completely autonomous or semi-autonomous way. Different tests were made to validate this work cell, showing the correct implementation and the possibility of replacing the human worker on this PCB assembly task.

Bus factor is a metric that identifies how resilient is the project to the sudden engineer turnover. It states the minimal number of engineers that have to be hit by a bus for a project to be stalled. Even though the metric is often discussed in the community, few studies consider its general relevance. Moreover, the existing tools for bus factor estimation focus solely on the data from version control systems, even though there exists other channels for knowledge generation and distribution. With a survey of 269 engineers, we find that the bus factor is perceived as an important problem in collective development, and determine the highest impact channels of knowledge generation and distribution in software development teams. We also propose a multimodal bus factor estimation algorithm that uses data on code reviews and meetings together with the VCS data. We test the algorithm on 13 projects developed at JetBrains and compared its results to the results of the state-of-the-art tool by Avelino et al. against the ground truth collected in a survey of the engineers working on these projects. Our algorithm is slightly better in terms of both predicting the bus factor as well as key developers compared to the results of Avelino et al. Finally, we use the interviews and the surveys to derive a set of best practices to address the bus factor issue and proposals for the possible bus factor assessment tool.

Cloud Computing (CC) has emerged as an on-demand accessible tool in different practical applications such as digital industry, academics, manufacturing, health sector and others. In this paper different security threats faced by CC are discussed with suitable examples. Moreover, an artificial intelligence based security enabled CC is also discussed based on suitable empirical data. It is found that an artificial neural network (ANN) is an effective system to detect the level of risk factors associated with CC along with mitigating those risk issues with appropriate algorithms. Hence, it provides a desired level of protection against cyber attacks, internal confidential threats and external threat of data theft from a cloud computing system. Levenberg–Marquardt (LMBP) algorithms are also found as a significant tool to estimate the level of security performance around a cloud computing system. ANN is used to improve the performance level of data security across a cloud computing network and make it security enabled to ensure a protected data transmission to clients associated with the system.

With the advent of the era of big data, information technology has been rapidly developed and the application of computers has been popularized. However, network technology is a double-edged sword. While providing convenience, it also faces many problems, among which there are many hidden dangers of network information security. Based on this, based on the era background of big data, the network information security analysis, explore the main network security problems, and elaborate computer information network security matters needing attention, to strengthen the network security management, and put forward countermeasures, so as to improve the level of network security.

The widespread application of industrial Internet identifiers has increased the security risks of industrial Internet and identifier resolution system. In order to improve the security capabilities of identifier resolution system, this paper analyzes the security challenges faced by identifier resolution system at this stage, and in line with the concept of layered security defense in depth, divides the security domains of identifier resolution system and proposes a multi-level security strategy based on security domains by deploying appropriate protective measures in each security domain.

The importance of the security of industrial control network has become increasingly prominent. Aiming at the defects of main security protection system in the intelligent manufacturing industrial control network, we propose a security attack risk detection and defense, and emergency processing capability synchronization technology system suitable for the intelligent manufacturing industrial control system. Integrating system control and network security theories, a flexible and reconfigurable system-wide security architecture method is proposed. On the basis of considering the high availability and strong real-time of the system, our research centers on key technologies supporting system-wide security analysis, defense strategy deployment and synchronization, including weak supervision system reinforcement and pattern matching, etc.. Our research is helpful to solve the problem of industrial control network of “old but full of loopholes” caused by the long-term closed development of the production network of important parts, and alleviate the contradiction between the high availability of the production system and the relatively backward security defense measures.

The risk of detecting incidents in the field of computer technology in Maritime transport is considered. The structure of the computer incident investigation system and its functions are given. The system of conducting investigations of computer incidents on sea transport is considered. A possible algorithm for investigating the incident using the tools of forensic science and an algorithm for transmitting the received data for further processing are presented.

With the development of openness, sharing and interconnection of computer network, the architecture of enterprise network becomes more and more complex, and various network security problems appear. Threat Intelligence(TI) Analysis and situation awareness(SA) are the prediction and analysis technology of enterprise security risk, while intrusion detection technology belongs to active defense technology. In order to ensure the safe operation of computer network system, we must establish a multi-level and comprehensive security system. This paper analyzes many security risks faced by enterprise computer network, and integrates threat intelligence analysis, security situation assessment, intrusion detection and other technologies to build a comprehensive enterprise security system to ensure the security of large enterprise network.

This paper proposes a lightweight digital signing scheme for supporting document signing on mobile devices connected to cloud computing. We employ elliptic curve (ECC) digital signature algorithm (ECDSA) for key pair generation done at mobile device and introduce outsourced proxy (OSP) to decrypt the encrypted file and compute hash value of the files stored in the cloud system. In our model, a mobile client invokes fixed-sized message digests to be signed with a private key stored in the device and produces the digital signature. Then, the signature is returned to the proxy for embedding it onto the original file. To this end, the trust between proxy and mobile devices is guaranteed by PKI technique. Based on the lightweight property of ECC and the modular design of our OSP, our scheme delivers the practical solution that allows mobile users to create their own digital signatures onto documents in a secure and efficient way. We also present the implementation details including system development and experimental evaluation to demonstrate the efficiency of our proposed system.

The security proposed for Vehicle-to-Everything (V2X) systems in the European Union is specified in the ETSI Cooperative Intelligent Transport System (C-ITS) standards, and related documents are based on the trusted PKI/CAs. The C-ITS trust model platform comprises an EU Root CA and additional Root CAs run in Europe by member state authorities or private organizations offering certificates to individual users. A new method is described in this paper where the security in V2X is based on the Distributed Public Keystore (DPK) platform developed for Ethereum blockchain. The V2X security is considered as one application of the DPK platform. The DPK stores and distributes the vehicles, RSUs, or other C-ITS role-players’ public keys. It establishes a generic key exchange/ agreement scheme that provides mutual key, entity authentication, and distributing a session key between two peers. V2X communication based on this scheme can establish an end-to-end (e2e) secure session and enables vehicle authentication without the need for a vehicle certificate signed by a trusted Certificate Authority.