Design of Platforms for Experimentation in Industrial Cybersecurity

Domí­nguez, Manuel; Fuertes, Juan J.; Prada, Miguel A.; Alonso, Serafí­n; Morán, Antonio; Perez, D. H. Campora

doi:10.3390/app12136520

Cited by 10 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, ethics and privacy must be considered in implementing AI in cybersecurity. The generation of synthetic data raises questions about the ethics of using fictitious or generated information, and it is essential to address these issues responsibly [51].…”

Section: Discussionmentioning

confidence: 99%

Developing a Cybersecurity Training Environment through the Integration of OpenAI and AWS

Villegas-Ch,

Govea,

Ortiz-Garces

2024

Applied Sciences

View full text Add to dashboard Cite

Cybersecurity is a critical concern in today’s digital age, where organizations face an ever-evolving cyber threat landscape. This study explores the potential of leveraging artificial intelligence and Amazon Web Services to improve cybersecurity practices. Combining the capabilities of OpenAI’s GPT-3 and DALL-E models with Amazon Web Services infrastructure aims to improve threat detection, generate high-quality synthetic training data, and optimize resource utilization. This work begins by demonstrating the ability of artificial intelligence to create synthetic cybersecurity data that simulates real-world threats. These data are essential for training threat detection systems and strengthening an organization’s resilience against cyberattacks. While our research shows the promising potential of artificial intelligence and Amazon Web Services in cybersecurity, it is essential to recognize the limitations. Continued research and refinement of AI models are needed to address increasingly sophisticated threats. Additionally, ethical and privacy considerations must be addressed when employing AI in cybersecurity practices. The results support the notion that this collaboration can revolutionize how organizations address cyber challenges, delivering greater efficiency, speed, and accuracy in threat detection and mitigation.

show abstract

Section: Discussionmentioning

confidence: 99%

Developing a Cybersecurity Training Environment through the Integration of OpenAI and AWS

Villegas-Ch,

Govea,

Ortiz-Garces

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In the face of complex threats, studies [3][4][5] have been conducted on the application of cyber defense methods for critical infrastructure based on knowledge of physical processes in the infrastructure. This approach enables the detection of traditional computer attacks that alter the behavior of the primary physical process in the infrastructure, based on the knowledge of the physical process in the cycle of infrastructure management.…”

Section: Methods Of Cyber Protection Of Critical Infrastructure Objectsmentioning

confidence: 99%

Application of Sentiment Analysis to Prevent Cyberattacks on Objects of Critical Information Infrastructure

Lehominova,

Shchavinsky,

Muzhanova

et al. 2023

IJC

View full text Add to dashboard Cite

The article addresses the pressing issue of ensuring cyber security for critical information infrastructure, which is associated with the development of modern information technologies and the increased potential for cyber attacks from criminal groups and potential adversary state entities. An analysis of the scientific literature indicates the necessity of preventive measures and scientific research, which involve monitoring the cyberspace. The application of sentiment analysis is proposed to detect the emotional sentiment towards critical information infrastructure objects. Following a defined algorithm, a sentiment analysis model is constructed based on an artificial neural network using open-source Python programming language libraries. The model's distinguishing feature is the consideration of emoticons to determine the intensification of emotional attitudes towards conducting cyber attacks on critical information infrastructure objects. A dataset related to cyber attacks from social media platforms such as Twitter and Instagram is collected to train the neural network. The results of training and testing the neural network provide grounds to assert that the network's accuracy of 0.7852 is relatively high, enabling its application by cyber reconnaissance units for early detection of cyber threats to critical infrastructure objects in combination with other tools.

show abstract

“…Elements such as pumps and relays serve as actuators. The HMI also demonstrates the data obtained from the sensors [6,7].…”

Section: Scada Systemmentioning

confidence: 99%

A Multi-Model Proposal for Classification and Detection of DDoS Attacks on SCADA Systems

SÖĞÜT

Erdem

2023

Applied Sciences

View full text Add to dashboard Cite

Industrial automation and control systems have gained increasing attention in the literature recently. Their integration with various systems has triggered considerable developments in critical infrastructure systems. With different network structures, these systems need to communicate with each other, work in an integrated manner, be controlled, and intervene effectively when necessary. Supervision Control and Data Acquisition (SCADA) systems are mostly utilized to achieve these aims. SCADA systems, which control and monitor the connected systems, have been the target of cyber attackers. These systems are subject to cyberattacks due to the openness to external networks, remote controllability, and SCADA-architecture-specific cyber vulnerabilities. Protecting SCADA systems on critical infrastructure systems against cyberattacks is an important issue that concerns governments in many aspects such as economics, politics, transport, communication, health, security, and reliability. In this study, we physically demonstrated a scaled-down version of a real water plant via a Testbed environment created including a SCADA system. In order to disrupt the functioning of the SCADA system in this environment, five attack scenarios were designed by performing various DDoS attacks, i.e., TCP, UDP, SYN, spoofing IP, and ICMP Flooding. Additionally, we evaluated a scenario with the baseline behavior of the SCADA system that contains no attack. During the implementation of the scenarios, the SCADA system network was monitored, and network data flow was collected and recorded. CNN models, LSTM models, hybrid deep learning models that amalgamate CNN and LSTM, and traditional machine learning models were applied to the obtained data. The test results of various DDoS attacks demonstrated that the hybrid model and the decision tree model are the most suitable for such environments, reaching the highest test accuracy of 95% and 99%, respectively. Moreover, we tested the hybrid model on a dataset that is used commonly in the literature which resulted in 98% accuracy. Thus, it is suggested that the security of the SCADA system can be effectively improved, and we demonstrated that the proposed models have a potential to work in harmony on real field systems.

show abstract

Design of Platforms for Experimentation in Industrial Cybersecurity

Cited by 10 publications

References 35 publications

Developing a Cybersecurity Training Environment through the Integration of OpenAI and AWS

Developing a Cybersecurity Training Environment through the Integration of OpenAI and AWS

Application of Sentiment Analysis to Prevent Cyberattacks on Objects of Critical Information Infrastructure

A Multi-Model Proposal for Classification and Detection of DDoS Attacks on SCADA Systems

Contact Info

Product

Resources

About