Faculty of Computing-Scopus

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4892

Browse

Filters

20252

Advanced Search

Filter by

Settings

Author: search.filters.author.Senarathne, AHas files: Yes

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemEmbargo
    Project HyperAdapt: An Agent-Based Intelligent Sandbox Design to Deceive and Analyze Sophisticated Malware
    (Institute of Electrical and Electronics Engineers Inc., 2025) Perera, S; Dias, S; Vithanage, V; Dilhara, A; Senarathne, A; Siriwardana, D; Liyanapathirana, C
    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.
  • Thumbnail Image
    ItemEmbargo
    Dynamic Resource Allocation and Management in SDN for Multi-Service Network
    (Institute of Electrical and Electronics Engineers Inc., 2025) Fernando U.S.K; Pieris M.H.N; Abhayathunge H.I; Athapattu A.R.B.L; Dharmakeerthi, U; Senarathne, A
    The increase in network traffic due to technological advancements has led to considerable network congestion, complicating manual network management. Software Defined Networking (SDN) addresses these limitations by decoupling the control plane from the data plane, thereby facilitating centralized and programmable network management. This study introduces a novel dynamic resource allocation method utilizing the Ryu controller and Mininet to optimize traffic flow by identifying congestion-free channels based on critical network attributes such as link bandwidth utilization, latency, and packet loss. The proposed method comprises four principal components: traffic categorization, a dynamic queuing system, an advanced status collection module, and a path selection module. The Ryu controller's dynamic packet direction based on priority levels ensures efficient resource utilization and improved Quality of Service (QoS). Simulated traffic scenarios demonstrate the efficacy of the proposed algorithm, hence highlighting its ability to enhance network performance beyond traditional static routing methods.