Enhancing Software Security with AI-Powered SDKs: A Framework for Proactive Threat Mitigation
DOI:
https://doi.org/10.15680/IJCTECE.2024.0702005Keywords:
AI-powered SDKs, software security, proactive threat mitigation, machine learning, vulnerability detection, secure software development lifecycleAbstract
With the increase of the complexity and interconnectedness among software, traditional reactionary security tools are incapable against advanced cyber threats. We develop a new class of AI-based Software Development Kit (SDK) framework that secures software baselines by systematically detecting potential security vulnerabilities in their initial development. The proposed solution is such that machine learning models are integrated directly with the SDK for real-time code analysis and security vulnerabilities detection, automatic threat identification and intelligent application of remediation. It uses supervised and unsupervised learning methods on a large set of both historical code and known vulnerabilities, to be able to identify insecure coding lines, to predict potential exploits and to give detailed feedbacks concerning possible errors. The framework’s effectiveness was evaluated on a case study over a cloud-based enterprise application. This approach across its volume of security projects resulted in a 40% reduction in the number of security incidents compared to baseline projects that were not developed with embedded AI and a 30% drop in the time it took to remediate vulnerabilities. According to developer surveys, security knowledge and confidence in a secure coding practice were increased following the product trial. These findings demonstrate the promise of incorporating AI-based functionality with SDKs based on a proactive, adaptive and scalable strategy for software security, as such a tool may contribute to modern secure software development lifecycles.
References
[1] J. Smith and A. Kumar, “AI in Cybersecurity: Enhancing Threat Detection Using Deep Learning,” IEEE Transactions on Cybernetics, vol. 52, no. 7, pp. 1098–1113, Jul. 2022.
[2] M. Brown et al., “Generative AI Models for Intrusion Detection in Cloud Networks,” Journal of Cloud Security, vol. 11, no. 4, pp. 223–239, Oct. 2022.
[3] Vadisetty R, Polamarasetti A, Prajapati S, Butani JB. AI-Driven Threat Detection: Enhancing Cloud Security with Generative Models for Real-Time Anomaly Detection and Risk Mitigation. SSRN 5218294, 2023 Jul 23.
[4] Nanda R. AI-Augmented Software-Defined Networking (SDN) in Cloud Environments. Int. J. of Artificial Intelligence, Data Science, and Machine Learning. 2023 Oct 28;4(4):1-9.
[5] Chen, Jiageng, Chunhua Su, and Zheng Yan. AI-Driven Cyber Security Analytics and Privacy Protection. Security and Communication Networks. 2019.
[6] Cooper, Mason. AI-Driven Early Threat Detection: Strengthening Cybersecurity Ecosystems with Proactive Cyber Defense Strategies. 2020.
[7] Sarker, Iqbal H., Md Hasan Furhad, and Raza Nowrozy. AI-driven cybersecurity: an overview, security intelligence modeling and research directions. SN Computer Science 2.3 (2021): 173.
[8] Maddireddy, Bhargava Reddy, and Bharat Reddy Maddireddy. Evolutionary Algorithms in AI-Driven Cybersecurity Solutions for Adaptive Threat Mitigation. Int. J. of Advanced Engineering Technologies and Innovations 1.2 (2021): 17-43.
[9] Peddamukkula, P. K. (2024). The Impact of AI-Driven Automated Underwriting on the Life Insurance Industry. International Journal of Computer Technology and Electronics Communication, 7(5), 9437-9446.
[10] Wiafe, I., Koranteng, F. N., Obeng, E. N., Assyne, N., Wiafe, A., & Gulliver, S. R. Artificial intelligence for cybersecurity: a systematic mapping of literature. IEEE Access, 8, 146598-146612 (2020).
[11] Lee, J., Kim, J., Kim, I., & Han, K. Cyber threat detection based on artificial neural networks using event profiles. IEEE Access, 7, 165607-165626 (2019).
[12] Nina, P., & Ethan, K. AI-Driven Threat Detection: Enhancing Cloud Security with Cutting-Edge Technologies. Int. J. of Trend in Scientific Research and Development, 4(1), 1362-1374 (2019).
[13] Kathirvel A, Maheswaran CP. Enhanced AI-Based intrusion detection and response system for WSN. Artificial Intelligence for Intrusion Detection Systems, 2023 Oct 16, pp. 155-177.
[14] C. Davis and S. Patel, “Variational Autoencoders for Anomaly Detection in Network Traffic,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 12– 24, Jan. 2022.
[15] W. Lee, “GAN-Based Attack Simulation for AI-Powered Security,” Cybersecurity and AI Review, vol. 9, no. 3, pp. 134–149, Sep. 2022.
[16] K. Wang and J. Luo, “Transformer-Based Approaches for Security Event Correlation,” IEEE Access, vol. 10, pp. 23844–23856, 2022.
[17] A. Singh, “Threat Mitigation in Cloud Environments Using AI-Driven Models,” Cloud Computing Security Journal, vol. 8, no. 2, pp. 177–192, Dec. 2022.
[18] R. Chen and H. Park, “Adversarial Machine Learning Attacks on AI-Driven Security Systems,” IEEE Transactions on Information Forensics and Security, vol. 18, pp. 99–112, Jan. 2023.
[19] B. Taylor et al., “Reducing False Positives in AI-Powered Threat Detection,” Journal of Cybersecurity Research, vol. 7, no. 3, pp. 45–61, Aug. 2022.
