Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization
This addresses the need for scalable cybersecurity solutions in real-world software systems, though it is incremental as it builds on existing techniques like knowledge distillation and optimization.
The paper tackles the problem of high computational and storage demands in deploying large pre-trained models for automated software vulnerability assessment by proposing a resource-efficient framework using knowledge distillation and particle swarm optimization, achieving a 99.4% reduction in model size while retaining 89.3% accuracy and outperforming baselines by 1.7% in accuracy with 60% fewer parameters.
The increasing complexity of software systems has led to a surge in cybersecurity vulnerabilities, necessitating efficient and scalable solutions for vulnerability assessment. However, the deployment of large pre-trained models in real-world scenarios is hindered by their substantial computational and storage demands. To address this challenge, we propose a novel resource-efficient framework that integrates knowledge distillation and particle swarm optimization to enable automated vulnerability assessment. Our framework employs a two-stage approach: First, particle swarm optimization is utilized to optimize the architecture of a compact student model, balancing computational efficiency and model capacity. Second, knowledge distillation is applied to transfer critical vulnerability assessment knowledge from a large teacher model to the optimized student model. This process significantly reduces the model size while maintaining high performance. Experimental results on an enhanced MegaVul dataset, comprising 12,071 CVSS (Common Vulnerability Scoring System) v3 annotated vulnerabilities, demonstrate the effectiveness of our approach. Our approach achieves a 99.4% reduction in model size while retaining 89.3% of the original model's accuracy. Furthermore, it outperforms state-of-the-art baselines by 1.7% in accuracy with 60% fewer parameters. The framework also reduces training time by 72.1% and architecture search time by 34.88% compared to traditional genetic algorithms.