COMPARATIVE ANALYZES SECURITY AI AND ML TRAINED MODELS
Article Sidebar
Main Article Content
Abstract:
Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing cybersecurity through advanced threat detection and prevention. This article compares the security challenges and methods used to safeguard trained models in AI and ML systems. It explores techniques for protecting model integrity, analyzes how these methods are applied to AI and ML, and presents a comparative analysis of their effectiveness in securing trained models.
Article Details
How to Cite:
References:
Mauri, L., & Damiani, E. (2022). Modeling Threats to AI-ML Systems Using STRIDE. Sensors. DOI: 10.3390/s22176662.
Ahmad, S. S., & Prasad, K. (2023). An Artificial Intelligence (AI) Enabled Framework for Cyber Security Using Machine Learning Techniques. International Research Journal. DOI: 10.61916/prmn.2023.v02i01.009.
Xu, Q., Arafin, M. T., & Qu, G. (2020). MIDAS: Model Inversion Defenses Using an Approximate Memory System. AsianHOST. DOI: 10.1109/AsianHOST51057.2020.9358254.
Mothukuri, V., Khare, P., & Srivastava, G. (2021). Federated-Learning-Based Anomaly Detection for IoT Security Attacks. IEEE IoT Journal. DOI: 10.1109/JIOT.2021.3077803.
Liu, Y., Tantithamthavorn, C., Li, L., & Liu, Y. (2022). Explainable AI for Android Malware Detection. ISSRE. DOI: 10.1109/ISSRE55969.2022.00026.