Visible to the public Biblio

Found 13520 results

Filters: Keyword is pubcrawl  [Clear All Filters]
Liu, Mengyao, Oostvogels, Jonathan, Michiels, Sam, Joosen, Wouter, Hughes, Danny.  2022.  BoboLink: Low Latency and Low Power Communication for Intelligent Environments. 2022 18th International Conference on Intelligent Environments (IE). :1—4.
Intelligent Environments (IEs) enrich the physical world by connecting it to software applications in order to increase user comfort, safety and efficiency. IEs are often supported by wireless networks of smart sensors and actuators, which offer multi-year battery life within small packages. However, existing radio mesh networks suffer from high latency, which precludes their use in many user interface systems such as real-time speech, touch or positioning. While recent advances in optical networks promise low end-to-end latency through symbol-synchronous transmission, current approaches are power hungry and therefore cannot be battery powered. We tackle this problem by introducing BoboLink, a mesh network that delivers low-power and low-latency optical networking through a combination of symbol-synchronous transmission and a novel wake-up technology. BoboLink delivers mesh-wide wake-up in 1.13ms, with a quiescent power consumption of 237µW. This enables building-wide human computer interfaces to be seamlessly delivered using wireless mesh networks for the first time.
Sebestyén, Gergely, Kopják, József.  2022.  Battery Life Prediction Model of Sensor Nodes using Merged Data Collecting methods. 2022 IEEE 20th Jubilee World Symposium on Applied Machine Intelligence and Informatics (SAMI). :000031—000034.
The aim of this paper is to describe the battery lifetime estimation and energy consumption model of the sensor nodes in TDMA wireless mesh sensor using merged data collecting (MDC) methods based on lithium thionyl chloride batteries. Defining the energy consumption of the nodes in wireless mesh networks is crucial for battery lifetime estimation. In this paper, we describe the timing, energy consumption, and battery lifetime estimation of the MDC method in the TDMA mesh sensor networks using flooding routing. For the battery life estimation, we made a semiempirical model that describes the energy consumption of the nodes with a real battery model. In this model, the low-level constraints are based on the measured energy consumption of the sensor nodes in different operation phases.
Choi, Jong-Young, Park, Jiwoong, Lim, Sung-Hwa, Ko, Young-Bae.  2022.  A RSSI-Based Mesh Routing Protocol based IEEE 802.11p/WAVE for Smart Pole Networks. 2022 24th International Conference on Advanced Communication Technology (ICACT). :1—5.
This paper proposes a RSSI-based routing protocol for smart pole mesh networks equipped with multiple IEEE 802.11p/WAVE radios. In the IEEE 802.11p based multi-radio multi-channel environments, the performance of traditional mesh routing protocols is severely degraded because of metric measurement overhead. The periodic probe messages for measuring the quality of each channel incurs a large overhead due to the channel switching delay. To solve such an overhead problem, we introduce a routing metric that estimates expected transmission time and proposes a light-weight channel allocation algorithm based on RSSI value only. We evaluate the performance of the proposed solution through simulation experiments with NS-3. Simulation results show that it can improve the network performance in terms of latency and throughput, compared to the legacy WCETT routing scheme.
Kopják, József, Sebestyén, Gergely.  2022.  Energy Consumption Model of Sensor Nodes using Merged Data Collecting Methods. 2022 IEEE 20th Jubilee World Symposium on Applied Machine Intelligence and Informatics (SAMI). :000027—000030.
This paper presents an energy consumption model of the sensor nodes in TDMA wireless mesh sensor network using merged data collecting (MDC) methods. Defining the energy consumption of the nodes in wireless mesh networks is crucial for battery lifetime estimation. In this paper, we describe the semiempirical model of the energy consumption of MDC method in the TDMA mesh sensor networks using flooding routing. In the model the low-level constraints are based on the measured energy consumption of the sensor nodes in the different operation phases.
Rethfeldt, Michael, Brockmann, Tim, Eckhardt, Richard, Beichler, Benjamin, Steffen, Lukas, Haubelt, Christian, Timmermann, Dirk.  2022.  Extending the FLExible Network Tester (Flent) for IEEE 802.11s WLAN Mesh Networks. 2022 IEEE International Symposium on Measurements & Networking (M&N). :1—6.
Mesh networks based on the wireless local area network (WLAN) technology, as specified by the standards amendment IEEE 802.11s, provide for a flexible and low-cost interconnection of devices and embedded systems for various use cases. To assess the real-world performance of WLAN mesh networks and potential optimization strategies, suitable testbeds and measurement tools are required. Designed for highly automated transport-layer throughput and latency measurements, the software FLExible Network Tester (Flent) is a promising candidate. However, so far Flent does not integrate information specific to IEEE 802.11s networks, such as peer link status data or mesh routing metrics. Consequently, we propose Flent extensions that allow to additionally capture IEEE 802.11s information as part of the automated performance tests. For the functional validation of our extensions, we conduct Flent measurements in a mesh mobility scenario using the network emulation framework Mininet-WiFi.
Illi, Elmehdi, Pandey, Anshul, Bariah, Lina, Singh, Govind, Giacalone, Jean-Pierre, Muhaidat, Sami.  2022.  Physical Layer Continuous Authentication for Wireless Mesh Networks: An Experimental Study. 2022 IEEE International Mediterranean Conference on Communications and Networking (MeditCom). :136—141.
This paper investigates the robustness of the received signal strength (RSS)-based physical layer authentication (PLA) for wireless mesh networks, through experimental results. Specifically, we develop a secure wireless mesh networking framework and apply the RSS-based PLA scheme, with the aim to perform continuous authentication. The mesh setup comprises three Raspberry-PI4 computing nodes (acting as Alice, Bob, and Eve) and a server. The server role is to perform the initial authentication when a new node joins the mesh network. After that, the legitimate nodes in the mesh network perform continuous authentication, by leveraging the RSS feature of wireless signals. In particular, Bob tries to authenticate Alice in the presence of Eve. The performance of the presented framework is quantified through extensive experimental results in an outdoor environment, where various nodes' positions, relative distances, and pedestrian speeds scenarios are considered. The obtained results demonstrate the robustness of the underlying model, where an authentication rate of 99% for the static case can be achieved. Meanwhile, at the pedestrian speed, the authentication rate can drop to 85%. On the other hand, the detection rate improves when the distance between the legitimate and wiretap links is large (exceeds 20 meters) or when Alice and Eve are moving in different mobility patterns.
Taleb, Sylia Mekhmoukh, Meraihi, Yassine, Mirjalili, Seyedali, Acheli, Dalila, Ramdane-Cherif, Amar, Gabis, Asma Benmessaoud.  2022.  Enhanced Honey Badger Algorithm for mesh routers placement problem in wireless mesh networks. 2022 International Conference on Advanced Aspects of Software Engineering (ICAASE). :1—6.
This paper proposes an improved version of the newly developed Honey Badger Algorithm (HBA), called Generalized opposition Based-Learning HBA (GOBL-HBA), for solving the mesh routers placement problem. The proposed GOBLHBA is based on the integration of the generalized opposition-based learning strategy into the original HBA. GOBL-HBA is validated in terms of three performance metrics such as user coverage, network connectivity, and fitness value. The evaluation is done using various scenarios with different number of mesh clients, number of mesh routers, and coverage radius values. The simulation results revealed the efficiency of GOBL-HBA when compared with the classical HBA, Genetic Algorithm (GA), and Particle Swarm optimization (PSO).
Nihtilä, Timo, Berg, Heikki.  2022.  Energy Consumption of DECT-2020 NR Mesh Networks. 2022 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). :196—201.
ETSI DECT-2020 New Radio (NR) is a new flexible radio interface targeted to support a broad range of wireless Internet of Things (IoT) applications. Recent reports have shown that DECT-2020 NR achieves good delay performance and it has been shown to fulfill both massive machine-type communications (mMTC) and ultra-reliable low latency communications (URLLC) requirements for 5th generation (5G) networks. A unique aspect of DECT-2020 as a 5G technology is that it is an autonomous wireless mesh network (WMN) protocol where the devices construct and uphold the network independently without the need for base stations or core network architecture. Instead, DECT-2020 NR relies on part of the network devices taking the role of a router to relay data through the network. This makes deployment of a DECT-2020 NR network affordable and extremely easy, but due to the nature of the medium access protocol, the routing responsibility adds an additional energy consumption burden to the nodes, who in the IoT domain are likely to be equipped with a limited battery capacity. In this paper, we analyze by system level simulations the energy consumption of DECT-2020 NR networks with different network sizes and topologies and how the reported low latencies can be upheld given the energy constraints of IoT devices.
Kalafatidis, Sarantis, Demiroglou, Vassilis, Mamatas, Lefteris, Tsaoussidis, Vassilis.  2022.  Experimenting with an SDN-Based NDN Deployment over Wireless Mesh Networks. IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). :1—6.
Internet of Things (IoT) evolution calls for stringent communication demands, including low delay and reliability. At the same time, wireless mesh technology is used to extend the communication range of IoT deployments, in a multi-hop manner. However, Wireless Mesh Networks (WMNs) are facing link failures due to unstable topologies, resulting in unsatisfied IoT requirements. Named-Data Networking (NDN) can enhance WMNs to meet such IoT requirements, thanks to the content naming scheme and in-network caching, but necessitates adaptability to the challenging conditions of WMNs.In this work, we argue that Software-Defined Networking (SDN) is an ideal solution to fill this gap and introduce an integrated SDN-NDN deployment over WMNs involving: (i) global view of the network in real-time; (ii) centralized decision making; and (iii) dynamic NDN adaptation to network changes. The proposed system is deployed and evaluated over the wiLab.1 Fed4FIRE+ test-bed. The proof-of-concept results validate that the centralized control of SDN effectively supports the NDN operation in unstable topologies with frequent dynamic changes, such as the WMNs.
Macabale, Nemesio A..  2022.  On the Stability of Load Adaptive Routing Over Wireless Community Mesh and Sensor Networks. 2022 24th International Conference on Advanced Communication Technology (ICACT). :21—26.
Wireless mesh networks are increasingly deployed as a flexible and low-cost alternative for providing wireless services for a variety of applications including community mesh networking, medical applications, and disaster ad hoc communications, sensor and IoT applications. However, challenges remain such as interference, contention, load imbalance, and congestion. To address these issues, previous work employ load adaptive routing based on load sensitive routing metrics. On the other hand, such approach does not immediately improve network performance because the load estimates used to choose routes are themselves affected by the resulting routing changes in a cyclical manner resulting to oscillation. Although this is not a new phenomenon and has been studied in wired networks, it has not been investigated extensively in wireless mesh and/or sensor networks. We present these instabilities and how they pose performance, security, and energy issues to these networks. Accordingly, we present a feedback-aware mapping system called FARM that handles these instabilities in a manner analogous to a control system with feedback control. Results show that FARM stabilizes routes that improves network performance in throughput, delay, energy efficiency, and security.
Fang, Wengao, Guan, Xiaojuan.  2022.  Research on iOS Remote Security Access Technology Based on Zero Trust. 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC). 6:238—241.

Under the situation of regular epidemic prevention and control, teleworking has gradually become a normal working mode. With the development of modern information technologies such as big data, cloud computing and mobile Internet, it's become a problem that how to build an effective security defense system to ensure the information security of teleworking in complex network environment while ensuring the availability, collaboration and efficiency of teleworking. One of the solutions is Zero Trust Network(ZTN), most enterprise infrastructures will operate in a hybrid zero trust/perimeter-based mode while continuing to invest in IT modernization initiatives and improve organization business processes. In this paper, we have systematically studied the zero trust principles, the logical components of zero trust architecture and the key technology of zero trust network. Based on the abstract model of zero trust architecture and information security technologies, a prototype has been realized which suitable for iOS terminals to access enterprise resources safely in teleworking mode.

Bobbert, Yuri, Scheerder, Jeroen.  2022.  Zero Trust Validation: from Practice to Theory : An empirical research project to improve Zero Trust implementations. 2022 IEEE 29th Annual Software Technology Conference (STC). :93—104.

How can high-level directives concerning risk, cybersecurity and compliance be operationalized in the central nervous system of any organization above a certain complexity? How can the effectiveness of technological solutions for security be proven and measured, and how can this technology be aligned with the governance and financial goals at the board level? These are the essential questions for any CEO, CIO or CISO that is concerned with the wellbeing of the firm. The concept of Zero Trust (ZT) approaches information and cybersecurity from the perspective of the asset to be protected, and from the value that asset represents. Zero Trust has been around for quite some time. Most professionals associate Zero Trust with a particular architectural approach to cybersecurity, involving concepts such as segments, resources that are accessed in a secure manner and the maxim “always verify never trust”. This paper describes the current state of the art in Zero Trust usage. We investigate the limitations of current approaches and how these are addressed in the form of Critical Success Factors in the Zero Trust Framework developed by ON2IT ‘Zero Trust Innovators’ (1). Furthermore, this paper describes the design and engineering of a Zero Trust artefact that addresses the problems at hand (2), according to Design Science Research (DSR). The last part of this paper outlines the setup of an empirical validation trough practitioner oriented research, in order to gain a broader acceptance and implementation of Zero Trust strategies (3). The final result is a proposed framework and associated technology which, via Zero Trust principles, addresses multiple layers of the organization to grasp and align cybersecurity risks and understand the readiness and fitness of the organization and its measures to counter cybersecurity risks.

Chen, Yan, Zhou, Xingchen, Zhu, Jian, Ji, Hongbin.  2022.  Zero Trust Security of Energy Resource Control System. 2022 IEEE 5th International Electrical and Energy Conference (CIEEC). :5052—5055.

The security of Energy Data collection is the basis of achieving reliability and security intelligent of smart grid. The newest security communication of Data collection is Zero Trust communication; The Strategy of Zero Trust communication is that don’t trust any device of outside or inside. Only that device authenticate is successful and software and hardware is more security, the Energy intelligent power system allow the device enroll into network system, otherwise deny these devices. When the device has been communicating with the Energy system, the Zero Trust still need to detect its security and vulnerability, if device have any security issue or vulnerability issue, the Zero Trust deny from network system, it ensures that Energy power system absolute security, which lays a foundation for the security analysis of intelligent power unit.

Wylde, Allison.  2021.  Zero trust: Never trust, always verify. 2021 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA). :1—4.

This short paper argues that current conceptions in trust formation scholarship miss the context of zero trust, a practice growing in importance in cyber security. The contribution of this paper presents a novel approach to help conceptualize and operationalize zero trust and a call for a research agenda. Further work will expand this model and explore the implications of zero trust in future digital systems.

Mohammed, Mahmood, Talburt, John R., Dagtas, Serhan, Hollingsworth, Melissa.  2021.  A Zero Trust Model Based Framework For Data Quality Assessment. 2021 International Conference on Computational Science and Computational Intelligence (CSCI). :305—307.

Zero trust security model has been picking up adoption in various organizations due to its various advantages. Data quality is still one of the fundamental challenges in data curation in many organizations where data consumers don’t trust data due to associated quality issues. As a result, there is a lack of confidence in making business decisions based on data. We design a model based on the zero trust security model to demonstrate how the trust of data consumers can be established. We present a sample application to distinguish the traditional approach from the zero trust based data quality framework.

Srikanth, K S, Ramesh, T K, Palaniswamy, Suja, Srinivasan, Ranganathan.  2022.  XAI based model evaluation by applying domain knowledge. 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). :1—6.
Artificial intelligence(AI) is used in decision support systems which learn and perceive features as a function of the number of layers and the weights computed during training. Due to their inherent black box nature, it is insufficient to consider accuracy, precision and recall as metrices for evaluating a model's performance. Domain knowledge is also essential to identify features that are significant by the model to arrive at its decision. In this paper, we consider a use case of face mask recognition to explain the application and benefits of XAI. Eight models used to solve the face mask recognition problem were selected. GradCAM Explainable AI (XAI) is used to explain the state-of-art models. Models that were selecting incorrect features were eliminated even though, they had a high accuracy. Domain knowledge relevant to face mask recognition viz., facial feature importance is applied to identify the model that picked the most appropriate features to arrive at the decision. We demonstrate that models with high accuracies need not be necessarily select the right features. In applications requiring rapid deployment, this method can act as a deciding factor in shortlisting models with a guarantee that the models are looking at the right features for arriving at the classification. Furthermore, the outcomes of the model can be explained to the user enhancing their confidence on the AI model being deployed in the field.
Yu, Jialin, Cristea, Alexandra I., Harit, Anoushka, Sun, Zhongtian, Aduragba, Olanrewaju Tahir, Shi, Lei, Moubayed, Noura Al.  2022.  INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations. 2022 International Joint Conference on Neural Networks (IJCNN). :1—8.
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.
Embarak, Ossama.  2022.  An adaptive paradigm for smart education systems in smart cities using the internet of behaviour (IoB) and explainable artificial intelligence (XAI). 2022 8th International Conference on Information Technology Trends (ITT). :74—79.
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.
Abeyagunasekera, Sudil Hasitha Piyath, Perera, Yuvin, Chamara, Kenneth, Kaushalya, Udari, Sumathipala, Prasanna, Senaweera, Oshada.  2022.  LISA : Enhance the explainability of medical images unifying current XAI techniques. 2022 IEEE 7th International conference for Convergence in Technology (I2CT). :1—9.
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.
Henriksen, Eilert, Halden, Ugur, Kuzlu, Murat, Cali, Umit.  2022.  Electrical Load Forecasting Utilizing an Explainable Artificial Intelligence (XAI) Tool on Norwegian Residential Buildings. 2022 International Conference on Smart Energy Systems and Technologies (SEST). :1—6.
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.
Lee, H., Lim, H., Lee, B..  2022.  Analysis of EV charging load impact on distribution network using XAI technique. CIRED Porto Workshop 2022: E-mobility and power distribution systems. 2022:167—170.
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.
Fujita, Koji, Shibahara, Toshiki, Chiba, Daiki, Akiyama, Mitsuaki, Uchida, Masato.  2022.  Objection!: Identifying Misclassified Malicious Activities with XAI. ICC 2022 - IEEE International Conference on Communications. :2065—2070.
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.
Barnard, Pieter, Macaluso, Irene, Marchetti, Nicola, DaSilva, Luiz A..  2022.  Resource Reservation in Sliced Networks: An Explainable Artificial Intelligence (XAI) Approach. ICC 2022 - IEEE International Conference on Communications. :1530—1535.
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.
Yeo, Guo Feng Anders, Hudson, Irene, Akman, David, Chan, Jeffrey.  2022.  A Simple Framework for XAI Comparisons with a Case Study. 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD). :501—508.
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.
Feng, Shuai, Cetinkaya, Ahmet, Ishii, Hideaki, Tesi, Pietro, De Persis, Claudio.  2021.  Resilient Quantized Control under Denial-of-Service with the Application of Variable Bit Rate Quantization. 2021 European Control Conference (ECC). :509–514.
In this paper, we investigate a networked control problem in the presence of Denial-of-Service (DoS) attacks, which prevent transmissions over the communication network. The communication between the process and controller is also subject to bit rate constraints. For mitigating the influences of DoS attacks and bit rate constraints, we develop a variable bit rate (VBR) encoding-decoding protocol and quantized controller to stabilize the control system. We show that the system’s resilience against DoS under VBR is preserved comparing with those under constant bit rate (CBR) quantized control, with fewer bits transmitted especially when the attack levels are low. The proposed VBR quantized control framework in this paper is general enough such that the results of CBR quantized control under DoS and moreover the results of minimum bit rate in the absence of DoS can be recovered.