In the rapidly advancing landscape of biotechnology, laboratories, and healthcare research, the criticality of robust cybersecurity risk management techniques cannot be overstated. As these industries increasingly rely on interconnected technologies and digitized data for innovation and patient care, they become attractive targets for malicious cyber threats. This chapter underscores the paramount importance for biotechnology companies, laboratories, and healthcare research organizations to develop real-world and practical cybersecurity risk management techniques. By proactively addressing cybersecurity vulnerabilities, these entities can safeguard their sensitive data, protect intellectual property, ensure patient privacy, and maintain the trust of stakeholders. This chapter emphasizes the necessity of adopting effective cybersecurity strategies tailored to the specific needs of each sector, taking into account the dynamic threat landscape and the potential consequences of cyber incidents.
1 January 2024 in Computer Modeling in Engineering & Sciences
Wireless technology is transforming the future of transportation through the development of the Internet of Vehicles (IoV). However, intricate security challenges are intertwined with technological progress: Vehicular ad hoc Networks (VANETs), a core component of IoV, face security issues, particularly the Black Hole Attack (BHA). This malicious attack disrupts the seamless flow of data and threatens the network’s overall reliability; also, BHA strategically disrupts communication pathways by dropping data packets from legitimate nodes altogether. Recognizing the importance of this challenge, we have introduced a new solution called ad hoc On-Demand Distance Vector-Reputation-based mechanism Local Outlier Factor (AODV-RL). The significance of AODV-RL lies in its unique approach: it verifies and confirms the trustworthiness of network components, providing robust protection against BHA. An additional safety layer is established by implementing the Local Outlier Factor (LOF), which detects and addresses abnormal network behaviors. Rigorous testing of our solution has revealed its remarkable ability to enhance communication in VANETs. Specifically, Our experimental results achieve message delivery ratios of up to 94.25% and minimal packet loss ratios of just 0.297%. Based on our experimental results, the proposed mechanism significantly improves VANET communication reliability and security. These results promise a more secure and dependable future for IoV, capable of transforming transportation safety and efficiency.
The escalating complexity and sophistication of software vulnerabilities demand innovative approaches in cybersecurity. This study introduces a groundbreaking framework, named “CodeSentry”, employing a transformer-based model for vulnerability detection in software code. “CodeSentry” leverages a finely-tuned version of the Generative Pre-trained Transformer (GPT), optimized for pinpointing vulnerable code patterns across various benchmark datasets. This approach stands apart by its remarkable computational efficiency, making it suitable for real-time applications − a significant advancement over traditional, resource-intensive deep learning models like CNNs and LSTMs. Empirical results showcase “CodeSentry” achieving an impressive 92.65% accuracy in vulnerability detection, surpassing existing state-of-the-art methods such as SyseVR and VulDeBERT. This novel methodology marks a paradigm shift in vulnerability detection, blending advanced AI with practical application efficiency.
The proliferation of the Internet of Things (IoT) devices has led to an increased risk of cyberattacks and malicious activities, including the spread of malware. To mitigate these risks, it is crucial to develop effective approaches for detecting IoT malware. In this study, we propose a framework for detecting IoT malware using optimized decision trees with AdaBoost. We use two widely used datasets, NSL-KDD and CICIDS2017, to evaluate the performance of the proposed framework. The framework includes feature selection and hyperparameter tuning to enhance the performance of the model. Our results show that the proposed framework achieves high accuracy, precision, recall, F1 score, and AUC-ROC in detecting malware attacks. However, the study also has limitations, such as the focus on network-level features and the limited evaluation on specific datasets. Future research can address these limitations by testing the proposed framework on more diverse datasets and exploring different machine learning algorithms and techniques. Overall, our study provides a promising approach to detect IoT malware and can contribute to the development of more robust and effective approaches for network intrusion detection.
Detecting software vulnerabilities is a critical task in ensuring the security of software systems. Recent advances in deep learning (DL) have shown promise in improving the accuracy of vulnerability detection. In this work, we proposed an approach for vulnerability detection using the Reformer language model. We compared our approach with previous works on three datasets: SARD, D2A, and Devign. Our experiments showed that our approach outperforms the state-of-the-art methods on all three datasets, achieving a precision of 0.95, recall of 0.91, and F1-score of 0.93 on average. Our approach is computationally efficient, making it suitable for large-scale vulnerability detection tasks. We also provide an in-depth analysis of the results and discuss the implications of our findings. Our work contributes to the growing body of literature on DL based vulnerability detection and demonstrates the potential of the Reformer model in this domain.
The efficacy of cybersecurity education and training relies on the availability of immersive, hands-on learning opportunities that nurture critical, creative, analytical, and problem-solving competencies. To accomplish this objective, it is imperative to develop activities that cultivate practical skills essential for careers in cybersecurity. This research aims to assess the potential of utilizing the Metaverse as a means of supporting cybersecurity education and training. We have created an immersive experience on the Metaverse in the form of a global contest, known as Capture the Flag (CTF), comprising three levels tailored to participants' expertise. Participants have the option to join the red, green, or blue team. The green team undertakes the development of a web or mobile application, or an IoT-based smart city, based on their interests, while the red team executes targeted attacks against the application or the smart city's control system, while blue team fix the application based on red team report. This is a cyclic process. This paper presents a proof of concept to evaluate the feasibility of establishing such an environment on the Metaverse. The system was constructed on a Unity gaming platform, incorporating network security elements. The virtual CTF serves as a replica of a real CTF/case study conducted over two consecutive academic semesters, during which teams constructed a secure messaging system utilizing secure coding and design principles. Our findings indicate that participants found this exercise exceptionally valuable in fostering critical and creative thinking skills, analytical skills, unconventional problem-solving skills, and team-building skills.