Around the world there has been an advancement of IoT edge devices, that in turn have enabled the collection of rich datasets as part of the Mobile Crowd Sensing (MCS) paradigm, which in practice is implemented in a variety of safety critical applications. In spite of the advantages of such datasets, there exists an inherent data trustworthiness challenge due to the interference of malevolent actors. In this context, there has been a great body of proposed solutions which capitalize on conventional machine algorithms for sifting through faulty data without any assumptions on the trustworthiness of the source. However, there is still a number of open issues, such as how to cope with strong colluding adversaries, while in parallel managing efficiently the sizable influx of user data. In this work we suggest that the usage of explainable artificial intelligence (XAI) can lead to even more efficient performance as we tackle the limitation of conventional black box models, by enabling the understanding and interpretation of a model s operation. Our approach enables the reasoning of the model s accuracy in the presence of adversaries and has the ability to shun out faulty or malicious data, thus, enhancing the model s adaptation process. To this end, we provide a prototype implementation coupled with a detailed performance evaluation under different scenarios of attacks, employing both real and synthetic datasets. Our results suggest that the use of XAI leads to improved performance compared to other existing schemes.

This study addresses the critical need to secure VR network communication from non-immersive attacks, employing an intrusion detection system (IDS). While deep learning (DL) models offer advanced solutions, their opacity as "black box" models raises concerns. Recognizing this gap, the research underscores the urgency for DL-based explainability, enabling data analysts and cybersecurity experts to grasp model intricacies. Leveraging sensed data from IoT devices, our work trains a DL-based model for attack detection and mitigation in the VR network, Importantly, we extend our contribution by providing comprehensive global and local interpretations of the model’s decisions post-evaluation using SHAP-based explanation.

Many studies of the adoption of machine learning (ML) in Security Operation Centres (SOCs) have pointed to a lack of transparency and explanation – and thus trust – as a barrier to ML adoption, and have suggested eXplainable Artificial Intelligence (XAI) as a possible solution. However, there is a lack of studies addressing to which degree XAI indeed helps SOC analysts. Focusing on two XAI-techniques, SHAP and LIME, we have interviewed several SOC analysts to understand how XAI can be used and adapted to explain ML-generated alerts. The results show that XAI can provide valuable insights for the analyst by highlighting features and information deemed important for a given alert. As far as we are aware, we are the first to conduct such a user study of XAI usage in a SOC and this short paper provides our initial findings.

The pervasive proliferation of digital technologies and interconnected systems has heightened the necessity for comprehensive cybersecurity measures in computer technological know-how. While deep gaining knowledge of (DL) has turn out to be a effective tool for bolstering security, its effectiveness is being examined via malicious hacking. Cybersecurity has end up an trouble of essential importance inside the cutting-edge virtual world. By making it feasible to become aware of and respond to threats in actual time, Deep Learning is a important issue of progressed security. Adversarial assaults, interpretability of models, and a lack of categorized statistics are all obstacles that want to be studied further with the intention to support DL-based totally security solutions. The protection and reliability of DL in our on-line world relies upon on being able to triumph over those boundaries. The present studies presents a unique method for strengthening DL-based totally cybersecurity, known as name dynamic adverse resilience for deep learning-based totally cybersecurity (DARDL-C). DARDL-C gives a dynamic and adaptable framework to counter antagonistic assaults by using combining adaptive neural community architectures with ensemble learning, real-time threat tracking, risk intelligence integration, explainable AI (XAI) for version interpretability, and reinforcement getting to know for adaptive defense techniques. The cause of this generation is to make DL fashions more secure and proof against the constantly transferring nature of online threats. The importance of simulation evaluation in determining DARDL-C s effectiveness in practical settings with out compromising genuine safety is important. Professionals and researchers can compare the efficacy and versatility of DARDL-C with the aid of simulating realistic threats in managed contexts. This gives precious insights into the machine s strengths and regions for improvement.

The stock market is a topic that is of interest to all sorts of people. It is a place where the prices change very drastically. So, something needs to be done to help the people risking their money on the stock market. The public s opinions are crucial for the stock market. Sentiment is a very powerful force that is constantly changing and having a significant impact. It is reflected on social media platforms, where almost the entire country is active, as well as in the daily news. Many projects have been done in the stock prediction genre, but since sentiments play a big part in the stock market, making predictions of prices without them would lead to inefficient predictions, and hence Sentiment analysis is very important for stock market price prediction. To predict stock market prices, we will combine sentiment analysis from various sources, including News and Twitter. Results are evaluated for two different cryptocurrencies: Ethereum and Solana. Random Forest achieved the best RMSE of 13.434 and MAE of 11.919 for Ethereum. Support Vector Machine achieved the best RMSE of 2.48 and MAE of 1.78 for Solana.

In this work, a novel framework for detecting mali-cious networks in the IoT-enabled Metaverse networks to ensure that malicious network traffic is identified and integrated to suit optimal Metaverse cybersecurity is presented. First, the study raises a core security issue related to the cyberthreats in Metaverse networks and its privacy breaching risks. Second, to address the shortcomings of efficient and effective network intrusion detection (NIDS) of dark web traffic, this study employs a quantization-aware trained (QAT) 1D CNN followed by fully con-nected networks (ID CNNs-GRU-FCN) model, which addresses the issues of and memory contingencies in Metaverse NIDS models. The QAT model is made interpretable using eXplainable artificial intelligence (XAI) methods namely, SHapley additive exPlanations (SHAP) and local interpretable model-agnostic ex-planations (LIME), to provide trustworthy model transparency and interpretability. Overall, the proposed method contributes to storage benefits four times higher than the original model without quantization while attaining a high accuracy of 99.82 \%.

Peer-to-peer (P2P) lenders face regulatory, compliance, application, and data security risks. A complete methodology that includes more than statistical and economic methods is needed to conduct credit assessments effectively. This study uses systematic literature network analysis and artificial intelligence to comprehend risk management in P2P lending financial technology. This study suggests that explainable AI (XAI) is better at identifying, analyzing, and evaluating financial industry risks, including financial technology. This is done through human agency, monitoring, transparency, and accountability. The LIME Framework and SHAP Value are widely used machine learning frameworks for data integration to speed up and improve credit score analysis using bank-like criteria. Thus, machine learning is expected to be used to develop a precise and rational individual credit evaluation system in peer-to-peer lending to improve credit risk supervision and forecasting while reducing default risk.

Security applications use machine learning (ML) models and artificial intelligence (AI) to autonomously protect systems. However, security decisions are more impactful if they are coupled with their rationale. The explanation behind an ML model s result provides the rationale necessary for a security decision. Explainable AI (XAI) techniques provide insights into the state of a model s attributes and their contribution to the model s results to gain the end user s confidence. It requires human intervention to investigate and interpret the explanation. The interpretation must align system s security profile(s). A security profile is an abstraction of the system s security requirements and related functionalities to comply with them. Relying on human intervention for interpretation is infeasible for an autonomous system (AS) since it must self-adapt its functionalities in response to uncertainty at runtime. Thus, an AS requires an automated approach to extract security profile information from ML model XAI outcomes. The challenge is unifying the XAI outcomes with the security profile to represent the interpretation in a structured form. This paper presents a component to facilitate AS information extraction from ML model XAI outcomes related to predictions and generating an interpretation considering the security profile.

Malware poses a significant threat to global cy-bersecurity, with machine learning emerging as the primary method for its detection and analysis. However, the opaque nature of machine learning s decision-making process of-ten leads to confusion among stakeholders, undermining their confidence in the detection outcomes. To enhance the trustworthiness of malware detection, Explainable Artificial Intelligence (XAI) is employed to offer transparent and comprehensible explanations of the detection mechanisms, which enable stakeholders to gain a deeper understanding of detection mechanisms and assist in developing defensive strategies. Despite the recent XAI advancements, several challenges remain unaddressed. In this paper, we explore the specific obstacles encountered in applying XAI to malware detection and analysis, aiming to provide a road map for future research in this critical domain.

Conventional approaches to analyzing industrial control systems have relied on either white-box analysis or black-box fuzzing. However, white-box methods rely on sophisticated domain expertise, while black-box methods suffers from state explosion and thus scales poorly when analyzing real ICS involving a large number of sensors and actuators. To address these limitations, we propose XAI-based gray-box fuzzing, a novel approach that leverages explainable AI and machine learning modeling of ICS to accurately identify a small set of actuators critical to ICS safety, which result in significant reduction of state space without relying on domain expertise. Experiment results show that our method accurately explains the ICS model and significantly speeds-up fuzzing by 64x when compared to conventional black-box methods.

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.

Many forms of machine learning (ML) and artificial intelligence (AI) techniques are adopted in communication networks to perform all optimizations, security management, and decision-making tasks. Instead of using conventional blackbox models, the tendency is to use explainable ML models that provide transparency and accountability. Moreover, Federate Learning (FL) type ML models are becoming more popular than the typical Centralized Learning (CL) models due to the distributed nature of the networks and security privacy concerns. Therefore, it is very timely to research how to find the explainability using Explainable AI (XAI) in different ML models. This paper comprehensively analyzes using XAI in CL and FL-based anomaly detection in networks. We use a deep neural network as the black-box model with two data sets, UNSW-NB15 and NSLKDD, and SHapley Additive exPlanations (SHAP) as the XAI model. We demonstrate that the FL explanation differs from CL with the client anomaly percentage.

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification \& robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows – user studies for explanation evaluation are conducted in only 14\% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.

Deep learning models are being utilized and further developed in many application domains, but challenges still exist regarding their interpretability and consistency. Interpretability is important to provide users with transparent information that enhances the trust between the user and the learning model. It also gives developers feedback to improve the consistency of their deep learning models. In this paper, we present a novel architectural design to embed interpretation into the architecture of the deep learning model. We apply dynamic pixel-wised weights to input images and produce a highly correlated feature map for classification. This feature map is useful for providing interpretation and transparent information about the decision-making of the deep learning model while keeping full context about the relevant feature information compared to previous interpretation algorithms. The proposed model achieved 92\% accuracy for CIFAR 10 classifications without finetuning the hyperparameters. Furthermore, it achieved a 20\% accuracy under 8/255 PGD adversarial attack for 100 iterations without any defense method, indicating extra natural robustness compared to other Convolutional Neural Network (CNN) models. The results demonstrate the feasibility of the proposed architecture.

The Zero-trust security architecture is a paradigm shift toward resilient cyber warfare. Although Intrusion Detection Systems (IDS) have been widely adopted within military operations to detect malicious traffic and ensure instant remediation against attacks, this paper proposed an explainable adversarial mitigation approach specifically designed for zero-trust cyber warfare scenarios. It aims to provide a transparent and robust defense mechanism against adversarial attacks, enabling effective protection and accountability for increased resilience against attacks. The simulation results show the balance of security and trust within the proposed parameter protection model achieving a high F1-score of 94\%, a least test loss of 0.264, and an adequate detection time of 0.34s during the prediction of attack types.

This study addresses the critical need to secure VR network communication from non-immersive attacks, employing an intrusion detection system (IDS). While deep learning (DL) models offer advanced solutions, their opacity as "black box" models raises concerns. Recognizing this gap, the research underscores the urgency for DL-based explainability, enabling data analysts and cybersecurity experts to grasp model intricacies. Leveraging sensed data from IoT devices, our work trains a DL-based model for attack detection and mitigation in the VR network, Importantly, we extend our contribution by providing comprehensive global and local interpretations of the model’s decisions post-evaluation using SHAP-based explanation.

At present, technological solutions based on artificial intelligence (AI) are being accelerated in various sectors of the economy and social relations in the world. Practice shows that fast-developing information technologies, as a rule, carry new, previously unidentified threats to information security (IS). It is quite obvious that identification of vulnerabilities, threats and risks of AI technologies requires consideration of each technology separately or in some aggregate in cases of their joint use in application solutions. Of the wide range of AI technologies, data preparation, DevOps, Machine Learning (ML) algorithms, cloud technologies, microprocessors and public services (including Marketplaces) have received the most attention. Due to the high importance and impact on most AI solutions, this paper will focus on the key AI assets, the attacks and risks that arise when implementing AI-based systems, and the issue of building secure AI.

With the use of AI and digital forensics, this paper outlines a complete strategy for handling security incidents in the cloud. The research is meant to improve cloud-based security issue detection and response. The results indicate the promise of this integrated strategy, with AI models improving the accuracy of issue detection and digital forensics speeding incident triage. Improved cloud security, proactive threat detection, optimized resource allocation, and conformity with legal and regulatory standards are only some of the practical consequences discussed in the paper. Advanced AI models, automated incident response, human-machine cooperation, threat intelligence integration, adversarial machine learning, compliance and legal issues, and cross-cloud security are all areas the report suggests further investigation into. In sum, this study aids in developing a more proactive and resilient strategy for handling cloud security incidents in a dynamic digital environment

The authors clarified in 2020 that the relationship between AI and security can be classified into four categories: (a) attacks using AI, (b) attacks by AI itself, (c) attacks to AI, and (d) security measures using AI, and summarized research trends for each. Subsequently, ChatGPT became available in November 2022, and the various potential applications of ChatGPT and other generative AIs and the associated risks have attracted attention. In this study, we examined how the emergence of generative AI affects the relationship between AI and security. The results show that (a) the need for the four perspectives of AI and security remains unchanged in the era of generative AI, (b) The generalization of AI targets and automatic program generation with the birth of generative AI will greatly increase the risk of attacks by the AI itself, (c) The birth of generative AI will make it possible to generate easy-to-understand answers to various questions in natural language, which may lead to the spread of fake news and phishing e-mails that can easily fool many people and an increase in AI-based attacks. In addition, it became clear that (1) attacks using AI and (2) responses to attacks by AI itself are highly important. Among these, the analysis of attacks by AI itself, using an attack tree, revealed that the following measures are needed: (a) establishment of penalties for developing inappropriate programs, (b) introduction of a reporting system for signs of attacks by AI, (c) measures to prevent AI revolt by incorporating Asimov s three principles of robotics, and (d) establishment of a mechanism to prevent AI from attacking humans even when it becomes confused.

The financial sector is such a world that is constantly under evolution, always with searches for the balance between strong security and the exponential increase of digital customer-centric operations. Here is where Albiometric recognition steps in, possibly contributing at the same time to efficiency and security for bank transactions. Therefore, this paper will help in studying the incorporation of AI in biometric authentication for banking activities and its impact from these dual perspectives. From the efficiency front, the paper will study how AI can make the user experience effective. This biometric recognition can be, for example, through fingerprint scanning or facial recognition, which will, at the These operations could be further streamlined with AI learning and adapting to user behavior, and even predicting actions and pre-populating transaction details. The traditional means of authentication, including passwords, are easily susceptible to phishing attacks and bruteforce hacking. On the other hand, this biometric data is unique for every individual and hence is more secure. AI can further cement this security by keeping an eye all the time for any anomaly or spoofing attempts in the biometric data. It means that machine-learning algorithms can identify even the slightest difference in fingerprints, facial features, or voice patterns, which human experts might oversee, and would provide a great help for security.

The network of smart physical object has a significant impact on the growth of urban civilization. The evidence has been cited from the digital sources such as scientific journals, conferences and publications, etc. Along with other security services, these kinds of structured, sophisticated data have addressed a number of security-related challenges. Here, many forms of cutting-edge machine learning and AI techniques are used to research how merging two or more algorithms with AI and ML might make the internet of things more safe. The main objective of this paper is it explore the applications of how ML and AI that can be used to improve IOT security.

Artificial Intelligence (AI) and Machine Learning (ML) models, while powerful, are not immune to security threats. These models, often seen as mere data files, are executable code, making them susceptible to attacks. Serialization formats like .pickle, .HDF5, .joblib, .ONNX etc. commonly used for model storage, can inadvertently allow arbitrary code execution, a vulnerability actively exploited by malicious actors. Furthermore, the execution environment for these models, such as PyTorch and TensorFlow, lacks robust sandboxing, enabling the creation of computational graphs that can perform I/O operations, interact with files, communicate over networks, and even spawn additional processes, underscoring the importance of ensuring the safety of the code executed within these frameworks. The emergence of Software Development Kits (SDKs) like ClearML, designed for tracking experiments and managing model versions, adds another layer of complexity and risk. Both open-source and enterprise versions of these SDKs have vulnerabilities that are just beginning to surface, posing additional challenges to the security of AI/ML systems. In this paper, we delve into these security challenges, exploring attacks, vulnerabilities, and potential mitigation strategies to safeguard AI and ML deployments.

Artificial Intelligence used in future networks is vulnerable to biases, misclassifications, and security threats, which seeds constant scrutiny in accountability. Explainable AI (XAI) methods bridge this gap in identifying unaccounted biases in black-box AI/ML models. However, scaffolding attacks can hide the internal biases of the model from XAI methods, jeopardizing any auditory or monitoring processes, service provisions, security systems, regulators, auditors, and end-users in future networking paradigms, including Intent-Based Networking (IBN). For the first time ever, we formalize and demonstrate a framework on how an attacker would adopt scaffoldings to deceive the security auditors in Network Intrusion Detection Systems (NIDS). Furthermore, we propose a detection method that auditors can use to detect the attack efficiently. We rigorously test the attack and detection methods using the NSL-KDD. We then simulate the attack on 5G network data. Our simulation illustrates that the attack adoption method is successful, and the detection method can identify an affected model with extremely high confidence.

We propose a conceptual framework, named "AI Security Continuum," consisting of dimensions to deal with challenges of the breadth of the AI security risk sustainably and systematically under the emerging context of the computing continuum as well as continuous engineering. The dimensions identified are the continuum in the AI computing environment, the continuum in technical activities for AI, the continuum in layers in the overall architecture, including AI, the level of AI automation, and the level of AI security measures. We also prospect an engineering foundation that can efficiently and effectively raise each dimension.

Despite the tremendous impact and potential of Artificial Intelligence (AI) for civilian and military applications, it has reached an impasse as learning and reasoning work well for certain applications and it generally suffers from a number of challenges such as hidden biases and causality. Next, “symbolic” AI (not as efficient as “sub-symbolic” AI), offers transparency, explainability, verifiability and trustworthiness. To address these limitations, neuro-symbolic AI has been emerged as a new AI field that combines efficiency of “sub-symbolic” AI with the assurance and transparency of “symbolic” AI. Furthermore, AI (that suffers from aforementioned challenges) will remain inadequate for operating independently in contested, unpredictable and complex multi-domain battlefield (MDB) environment for the foreseeable future and the AI enabled autonomous systems will require human in the loop to complete the mission in such a contested environment. Moreover, in order to successfully integrate AI enabled autonomous systems into military operations, military operators need to have assurance that these systems will perform as expected and in a safe manner. Most importantly, Human-Autonomy Teaming (HAT) for shared learning and understanding and joint reasoning is crucial to assist operations across military domains (space, air, land, maritime, and cyber) at combat speed with high assurance and trust. In this paper, we present a rough guide to key research challenges and perspectives of neuro symbolic AI for assured and trustworthy HAT.