ABSTRACT
The emergence of drone-based innovative cyber security solutions integrated with the Internet of Things (IoT) has revolutionized navigational technologies with robust data communication services across multiple platforms. This advancement leverages machine learning and deep learning methods for future progress. In recent years, there has been a significant increase in the utilization of IoT-enabled drone data management technology. Industries ranging from industrial applications to agricultural advancements, as well as the implementation of smart cities for intelligent and efficient monitoring. However, these latest trends and drone-enabled IoT technology developments have also opened doors to malicious exploitation of existing IoT infrastructures. This raises concerns regarding the vulnerability of drone networks and security risks due to inherent design flaws and the lack of cybersecurity solutions and standards. The main objective of this study is to examine the latest privacy and security challenges impacting the network of drones (NoD). The research underscores the significance of establishing a secure and fortified drone network to mitigate interception and intrusion risks. The proposed system effectively detects cyber-attacks in drone networks by leveraging deep learning and machine learning techniques. Furthermore, the model's performance was evaluated using well-known drones' CICIDS2017, and KDDCup 99 datasets. We have tested the multiple hyperparameter parameters for optimal performance and classify data instances and maximum efficacy in the NoD framework. The model achieved exceptional efficiency and robustness in NoD, specifically while applying B-LSTM and LSTM. The system attains precision values of 89.10% and 90.16%, accuracy rates up to 91.00-91.36%, recall values of 81.13% and 90.11%, and F-measure values of 88.11% and 90.19% for the respective evaluation metrics.
ABSTRACT
A significant percentage of security research that is conducted suffers from common issues that prevent wide-scale adoption. Common snags of such proposed methods tend to include (i) introduction of additional nodes within the communication architecture, breaking the simplicity of the typical client-server model, or fundamental restructuring of the Internet ecosystem; (ii) significant inflation of responsibilities or duties for the user and/or server operator; and (iii) adding increased risks surrounding sensitive data during the authentication process. Many schemes seek to prevent brute-forcing attacks; they often ignore either partially or holistically the dangers of other cyber-attacks such as MiTM or replay attacks. Therefore, there is no incentive to implement such proposals, and it has become the norm instead to inflate current username/password authentication systems. These have remained standard within client-server authentication paradigms, despite insecurities stemming from poor user and server operator practices, and vulnerabilities to interception and masquerades. Besides these vulnerabilities, systems which revolve around secure authentication typically present exploits of two categories; either pitfalls which allow MiTM or replay attacks due to transmitting data for authentication constantly, or the storage of sensitive information leading to highly specific methods of data storage or facilitation, increasing chances of human error. This paper proposes a more secure method of authentication that retains the current structure of accepted paradigms, but minimizes vulnerabilities which result from the process, and does not inflate responsibilities for users or server operators. The proposed scheme uses a hybrid, layered encryption technique alongside a two-part verification process, and provides dynamic protection against interception-based cyber-attacks such as replay or MiTM attacks, without creating additional vulnerabilities for other attacks such as bruteforcing. Results show the proposed mechanism outperforms not only standardized methods, but also other schemes in terms of deployability, exploit resilience, and speed.
