Cyber Data Research Articles

PLLM-CS: Pre-trained Large Language Model (LLM) for cyber threat detection in satellite networks

Satellite networks are vital in facilitating communication services for various critical infrastructures. These networks can seamlessly integrate with a diverse array of systems. However, some of these systems are vulnerable due to the absence of effective intrusion detection systems, which can be attributed to limited research and the high costs associated with deploying, fine-tuning, monitoring, and responding to security breaches. To address these challenges, we propose a pre-trained Large Language Model for Cyber Security, for short PLLM-CS, which is a variant of pre-trained Transformers, which includes a specialized module for transforming network data into contextually suitable inputs. This transformation enables the proposed LLM to encode contextual information within the cyber data. To validate the efficacy of the proposed method, we conducted empirical experiments using two publicly available network datasets, UNSW_NB 15 and TON_IoT, both providing Internet of Things (IoT)-based traffic data. Our experiments demonstrate that proposed LLM method outperforms state-of-the-art techniques such as BiLSTM, GRU, and CNN. Notably, the PLLM-CS method achieves an outstanding accuracy level of 100% on the UNSW_NB 15 dataset, setting a new standard for benchmark performance in this domain.

Meet Me in the Middle: Evaluating Middle Power Cyber Doctrine and Strategic Culture Through the Cases of Canada and Australia

The global expansion in reliance on information and communication technologies has thrust the digital world of cyberspace into the forefront of strategic security discourse. Meanwhile, the responsibilities, capabilities, and strategic interests of middle powers have been fraught with ambiguity and debate in international relations literature. While existing studies examine how the cyberspace domain has become an increasingly competitive arena for geopolitics and strategic competition between and among great powers, there remains a dearth of literature evaluating cyberspace objectives and behaviour for middle powers. This paper aims to fill this gap, drawing on prior frameworks of analysis used for great power cyber studies, alongside extant middle power literature, to employ the theoretical lens of strategic culture toward evaluating the unique behaviour of middle powers in cyberspace. This paper thus suggests that cyberspace presents scholars with an outlet to further examine and define middle powers in the international realm, as well as middle powers with opportunities to assert and potentially expand their position in the global order, while protecting and promoting their distinct interests. This paper also incorporates a synthesis of quantitative and qualitative cyber data, and the deployment of a Most Similar Systems Design to assess two middle power case studies: Canada and Australia. The findings help to challenge and refine our understanding of what roles, capabilities and objectives define middle power behaviour in cyberspace, as well as provide insight into the implications that the rise of cyber operations and security considerations might have for Canadian and Australian grand strategy, and middle power strategic culture more generally. Ultimately, this study serves to refine past theoretical assumptions in the context of a novel and expanding domain for statecraft and competition, and identify a foundation from which the principles of a more coherent and effective cyber doctrine for middle powers might be pursued.

Insuring Data Risks: Problems and Solutions

The proliferation of valuable data assets and connectivity in the digital economy has been accompanied by intensifying cyber risks. However, systemic constraints including data ambiguities, legal uncertainty, and misaligned incentives have severely limited advancement of cyber insurance coverage relative to rising enterprise protection needs. This research provides a comprehensive analysis of key bottlenecks inhibiting cyber data risk insurability. It examines constraints stemming from historical data deficiencies, risk modeling complexities, opaque controls, and fragmented regulatory regimes. The study also evaluates internal challenges faced by insurers in advancing policies like claims ambiguities, talent gaps, and reliance on primitive actuarial techniques. It further proposes targeted legal, risk management and public-private partnership enhancements that can expand viable transfer of cyber data risks. These include graduated security frameworks, transparent data exchanges, resilience incentives, risk pooling structures and international cooperation. With balanced reforms, cyber insurance can systematically enable enterprises to secure data assets commensurate with their rising economic and societal value.

How the process of discovering cyberattacks biases our understanding of cybersecurity

Social scientists do not directly study cyberattacks; they draw inferences from attack reports that are public and visible. Like human rights violations or war casualties, there are missing cyberattacks that researchers have not observed. The existing approach is to either ignore missing data and assume they do not exist or argue that reported attacks accurately represent the missing events. This article is the first to detail the steps between attack, discovery and public report to identify sources of bias in cyber data. Visibility bias presents significant inferential challenges for cybersecurity – some attacks are easy to observe or claimed by attackers, while others take a long time to surface or are carried out by actors seeking to hide their actions. The article argues that missing attacks in public reporting likely share features of reported attacks that take the longest to surface. It builds on datasets of cyberattacks by or against Five Eyes (an intelligence alliance composed of Australia, Canada, New Zealand, the United Kingdom and the United States) governments and adds new data on when attacks occurred, when the media first reported them, and the characteristics of attackers and techniques. Leveraging survival models, it demonstrates how the delay between attack and disclosure depends on both the attacker’s identity (state or non-state) and the technical characteristics of the attack (whether it targets information confidentiality, integrity, or availability). The article argues that missing cybersecurity events are least likely to be carried out by non-state actors or target information availability. Our understanding of ‘persistent engagement,’ relative capabilities, ‘intelligence contests’ and cyber coercion rely on accurately measuring restraint. This article’s findings cast significant doubt on whether researchers have accurately measured and observed restraint, and informs how others should consider external validity. This article has implications for our understanding of data bias, empirical cybersecurity research and secrecy in international relations.

Enhancing Security Frameworks with Artificial Intelligence in Cybersecurity

Cybersecurity, in the digital era we live in today, has become a major concern that demands innovation. Data Science and Artificial Intelligence (AI) have played a central role in changing the way we understand and address cyber threats. This research will review the important role of innovation in this technology in improving an organization's ability to detect, prevent, and respond to cyber attacks. Identifying patterns and gaining insights from security events in cyber data, while developing appropriate data-based models, is a key element in realizing automated and intelligent security systems. This research reviews needs in the cyber security domain that can be addressed through Artificial Intelligence (AI) techniques. In this study, we employed quantitative methods to assess the impact of artificial intelligence on enhancing cybersecurity by distributing questionnaires to 85 respondents, which included companies operating in the banking and IT sectors. In addition, this research will explore how data-based intelligent decision-making systems are able to protect systems from known and unknown cyber attacks. This research will conclude by considering the future potential of Artificial Intelligence and cybersecurity.

Secure Framework for Cyber Data Using Cryptographic and Steganographic Algorithms

The e-commerce industry has recently seen enormous growth on a global scale. Due to the rising popularity of online shopping, consumers, businesses, and depository financial institutions are extremely worried about debit/credit card fraud and the protection of personal information. It is essential to prevent unwanted access to and use of the information since it is disseminated over insecure channels. Cryptography and steganography are most frequently employed to avoid unauthorized access to sensitive data. However, the combined qualities of these two approaches are not secure enough in the modern world. It might lead to some vulnerability. It is possible to add additional layers of protection and achieve high levels of information security if visual cryptography is used in conjunction with the abovementioned combination. This research work proposed a multi-level information security framework for cyber data using random public key cryptography for the secret text, color image steganography for concealing secret encrypted text in the cover image, visual cryptography for slicing the cover image into two shares, and image steganography again to hide both the shares into two color images, respectively. These security processes significantly increase the confidentiality, dependability, and efficiency of secret messages. While there isn't a parameter to demonstrate the level of security achieved using cutting-edge techniques, the accuracy of the received text data is calculated in terms of MSE and correlation coefficient by comparing the sent and received text data. To evaluate the effectiveness of the suggested strategy, the time required at the transmitter and receiver ends is also calculated. The MATLAB environment is utilized in the implementation, demonstrating that the suggested system has improved robustness when considering steganalysis.

TikTok's Conflict of Interest with the US Government: Between Big Data Security and Economics (2017-2023)

State capabilities in securing cyberspace will determine national security in the real world because cyber data is related to conventional information. This condition makes cybersecurity a complex domain because of its virtual nature, but it can impact aspects in real space. This complexity is also because all parties can access cyber, causing conflicts such as competition for big data interests. This study aims to determine the dispute between TikTok and the United States government over the security of its users' data, especially users from the United States. The United States accuses TikTok of misusing US user data for Chinese intelligence. However, TikTok has denied the allegations. The qualitative method used in this research is based on data collection techniques through a literature study with secondary data support. As a result, TikTok requires user data for product and service development purposes. While the United States is more than that, big data users are a national asset determining their global economic position. There is no hard evidence to suggest that TikTok provided the Chinese government with the data of users from the United States. This paper also views the US government's interest as an extension of the local private sector. This view is based on the finding that TikTok's profits and popularity are far above their all-American competitors.

Duopoly insurers’ incentives for data quality under a mandatory cyber data sharing regime

We study the impact of data sharing policies on cyber insurance markets. These policies have been proposed to address the scarcity of data about cyber threats, which is essential to manage cyber risks. We propose a Cournot duopoly competition model in which two insurers choose the number of policies they offer (i.e., their production level) and also the resources they invest to ensure the quality of data regarding the cost of claims (i.e., the data quality of their production cost). We find that enacting mandatory data sharing sometimes creates situations in which at most one of the two insurers invests in data quality, whereas both insurers would invest when information sharing is not mandatory. This raises concerns about the merits of making data sharing mandatory.

An Analysis of Cyber Breaches and Effects on Shareholder Wealth

Cyber data breaches are an evolving risk facing all firms and threatens their ability to conduct business activity. Due to a lack of available information, very little is known about the frequency and severity of data breaches and the financial markets’ responses to them. This study uses a unique proprietary data set that includes cyber data breach information for 3,992 publicly traded firms during the 1990 to 2019 period. We find cyber breaches vary with time and cyber criminals focus on particular industries, types of information, access sources, and countries. We find significant short run negative abnormal returns around the announcement of cyber events and larger negative returns in industries with higher frequencies of attacks and attacks involving personal financial information. Additionally, we find increasing negative cumulative abnormal returns up to 250 days after the announcement.

PREVENTION OF COMPUTER CRIME THROUGH KNOWLEDGE OF THE CONCEPT OF CYBER SECURITY

The purpose of this article is to make the reader aware of the concept of cyber security and of the importance of establishing cyber data protection systems that we currently manage. Cyber-attacks have experienced a continuous upward trend in recent years, being targeted at both personal computer systems, computer systems managed by companies or computer systems managed by state institutions, as such cyber security has become a necessity for any user, provider, or consumer of cyber data.

Cyberattack Defense With Cyber-Physical Alert and Control Logic in Industrial Controllers

Power system substations have intelligent electronic devices (IEDs) that collect data and control other devices. As the bridge between the physical and cyber parts of the power system, IEDs capture some key system behaviors. Since adversaries can modify the system’s behavior, physical and cyber data can be used to infer characteristics about the adversary. In this article, we present alert and control logic for hardware-based power system defense using the physical data and communication status in substation IEDs for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cyber threat detection</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cyber-physical contingency detection and response</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">physical contingency identification and response</i> . The proposed alert and control logic routines are implemented in an industrial real-time automation controller using IEC 61131-3 in the resilient energy systems lab testbed. The goal is to help operators identify adversaries and protect the power grid in a cyber-physical environment. The effectiveness and accuracy of logic schemes are validated under different adversarial scenarios. Comparing the proposed schemes with an intrusion detection system, Snort, our results also suggest the benefits of using cyber and physical data to identify threats. The results also suggest the use of such hardware-based schemes with software algorithms in a next-generation cyber-physical energy management system, which can implement automatic control actions to protect power grids and its physical equipment against cyber threats.

Transmission Mysteries: Art and Technophilia

Transmission Mysteries: Art and Technophilia

Generating realistic cyber data for training and evaluating machine learning classifiers for network intrusion detection systems

Cyberspace operations, in conjunction with artificial intelligence and machine learning enhanced cyberspace infrastructure, make it possible to connect sensors directly to shooters independent of human control. These technologies serve as the pivot around which cyber data from the military’s Internet of Battlefield Things, for example, will be turned into actionable insight and knowledge and, ultimately, an information advantage for the military. As such, network intrusion detection systems must detect, evaluate, and respond to malicious cyber traffic at machine speed. Generative adversarial networks and variational autoencoders are fit as generative models with labeled cyber data from a real military enterprise network. These generative models are used to create realistic, synthetic cyber data. A combination of real and synthetic cyber data sets are then used to train several machine learning models for network intrusion detection. Purely synthetic data is shown to be statistically similar to the real data. There is no statistically significant difference in the performance of classifiers trained with real data versus a combination of real and synthetic data; however, classifiers trained with only synthetic data underperformed. To avoid a decrease in intrusion detection performance, classifiers must be trained with at least 15% real data.

Democracy and cyberconflict: how regime type affects state-sponsored cyberattacks

ABSTRACT A large body of research in international relations has focused on the relationship between regime type (i.e., the degree a nation is democratic or authoritarian) and traditional military conflict between states. However, to date, no research has examined how regime type affects conflict in the cyber domain. Thus, we attempt to analyze the effect regime type has on the initiation of state-sponsored cyberattacks. We examine 143 states from 2005 - 2013 utilizing cyber data on known state-sponsored cyberattacks taken from the Council on Foreign Relations Cyber Operations Tracker dataset (CFR-COTD) and economic, political, military, and social data collected by the authors. In conducting a cross-sectional, time series analysis we find that democratic institutions have a pacifying effect on the initiation of state-sponsored cyberattacks.

Fraud Detection in Supply Chain with Machine Learning

A variety of fraud in Supply Chains may be detected either in physical parts or in cyber data. We use supervised machine learning to detect various fraud and misinformation in supply chains. The study is based on a car manufacturer concerned with increasing fraud, ranging from fraudulent invoices to inflated prices. Big data is provided for pattern recognition. A macro-level code is presented with actual algorithms developed in Python. The research is continuing, while the current work is presented with promising results.

A Proposed SEC Cyber Data Disclosure Advisory Commission

A Proposed SEC Cyber Data Disclosure Advisory Commission

BCT-CS: Blockchain Technology Applications for Cyber Defense and Cybersecurity: A Survey and Solutions

Blockchain technology has now emerged as a ground-breaking technology with possible solutions to applications from securing smart cities to e-voting systems. Although it started as a digital currency or cryptocurrency, bitcoin, there is no doubt that blockchain is influencing and will influence business and society more in the near future. We present a comprehensive survey of how blockchain technology is applied to provide security over the web and to counter ongoing threats as well as increasing cybercrimes and cyber-attacks. During the review, we also investigate how blockchain can affect cyber data and information over the web. Our contributions included the following: (i) summarizing the Blockchain architecture and models for cybersecurity (ii) classifying and discussing recent and relevant works for cyber countermeasures using blockchain (iii) analyzing the main challenges and obstacles of blockchain technology in response to cyber defense and cybersecurity and (iv) recommendations for improvement and future research on the integration of blockchain with cyber defense.

Secure Data Validation and Transmission in Cloud and IoT Through Ban Logic and KP-ABE

Background: Cloud computing is a service that is being accelerating its growth in the field of information technology in recent years. Privacy and security are challenging issues for cloud users and providers. Obective: This work aims at ensuring secured validation of user and protects data during transmission for users in a public IoT-cloud environment. Existing security measures however fails by their single level of security, adaptability for large amount of data and reliability. Therefore, to overcome these issues and to achieve a better solution for vulnerable data. Method: The suggested method utilizes a secure transmission in cloud using key policy attribute based encryption (KPABE). Initially, user authentication is verified. Then the user data is encrypted with the help of KP-ABE algorithm. Finally, data validation and privacy preservation are done by Burrows-Abadi-Needham (BAN) logic. This verified, and shows that the proposed encryption is correct, secure and efficient to prevent unauthorized access and prevention of data leakage so that less chances of data/identity, theft of a user is the analysis and performed by KP-ABE, that is access control approach. Results: Here the method attains the maximum of 88.35% of validation accuracy with a minimum 8.78ms encryption time, which is better when, compared to the existing methods. The proposed mechanism is done by MATLAB. The performance of the implemented method is calculated based on the time of encryption and decryption, execution time and validation accuracy. Conclusion: Thus the proposed approach attains the high IoT-cloud data security and increases the speed for validation and transmission with high accuracy and used for cyber data science processing.

AUTOMATED STORAGE AND RETRIEVAL SYSTEM AN ALTERNATIVE FOR LOGISTIC TRANSFORMATION TECHNOLOGY: A CASE STUDY

This research was taken at one of the mechanical engineering companies produces customize spare parts, special purposed machinery, automation system integrator and robotic installation. The company has problem high cost operation warehouse, need space expanding production line, stockopname problem, picking failure, high cycle time operation, logistic efficiency, and inventory cost. These problems have impact to company performance which need cost down, increase efficiency and productivity with minimum defect. The data has shown company needs additional 157m2 to expanding new line, has 4% picking defect, there is 200 million operational cost over, 150sec cycle time, 7% lost part and risk cyber data security. Due to the importance of the problem, the company needs to evaluate and solve the problem which has impact to company performance, especially in the warehouse. DMAIC (Define Measure Analyze Improve and Control) approach is applied to comprehensively explore the problem and comes out with alternatives solution. Two alternatives were developed. The criteria for selection used were i.e. cost; accuracy, security, safety, productivity, cycle time, and minimize defect It was concluded that the application of automated storage and retrieval system (ASRS) was selected as it dominates in many aspects compare to expanding the current one. This implementation of ASRS approved that this new system answers the current warehouse problem

Detection of false data cyber-attacks for the assessment of security in smart grid using deep learning

Smart Grid uses electricity and information flows to set up a highly developed, fully automated, and distributed electricity grid system. To identify the reliability of work and availability, cyber attacks detection in the smart grids play a significant role. This paper highlights the integrity of false data cyber-attacks in the physical layers of smart grids. As the first contribution, the Proposed True Data Integrity provides an attack exposure metric through an Agent-Based Model. Next, the research focuses on the decentralization of Data Integrity Security in the system with an Agent-based approach. Finally, the productivity and efficiency of the developed modeling techniques are experimentally evaluated and compared with the existing state-of-the-art supervised deep-learning models. The obtained results of the studies have shown the improved false data detection accuracy of 98.19% through replay cyber-attacks using the Artificial Feed-forward Network. Based on the research findings, deep neural network can be used to assess cyber data in smart grids to detect malware incidents and attacks.