Project HyperAdapt: An Agent-Based Intelligent Sandbox Design to Deceive and Analyze Sophisticated Malware
Shamalka Perera, S. M. D. T. H. Dias, Vishwadinu Vithanage, Avishka Dilhara, Amila Nuwan Senarathne, Deemantha Siriwardana, Chethana Liyanapathirana · 2025
Malware increasingly employs sophisticated evasion techniques to bypass sandbox-based analysis, rendering traditional detection methods ineffective. This research presents Project HyperAdapt: Agent-Based Intelligent Sandbox, a framework that integrates both offensive and defensive machine learning models to enhance malware detection, deception, and behavioral analysis. The offensive RL model generates evasive malware samples, challenging the sandbox, while the defensive models including hybrid evasion detection, GAN-based behavior simulation, and a dynamically adapting RL agent work collectively to improve sandbox resilience. By continuously learning from evasive malware behavior, the defensive RL agent adapts in real-time, strengthening detection capabilities. Experimental results demonstrate that this approach enhances sandbox effectiveness, ensuring long-term adaptability against evolving malware threats.