We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
CODESENTRY: REVOLUTIONIZING REAL-TIME SOFTWARE VULNERABILITY DETECTION WITH OPTIMIZED GPT FRAMEWORK.
- Authors
JONES, Angel; OMAR, Marwan
- Abstract
The escalating complexity and sophistication of software vulnerabilities demand innovative approaches in cybersecurity. This study introduces a groundbreaking framework, named "CodeSentry", employing a transformer-based model for vulnerability detection in software code. "CodeSentry" leverages a finely-tuned version of the Generative Pre-trained Transformer (GPT), optimized for pinpointing vulnerable code patterns across various benchmark datasets. This approach stands apart by its remarkable computational efficiency, making it suitable for real-time applications - a significant advancement over traditional, resource-intensive deep learning models like CNNs and LSTMs. Empirical results showcase "CodeSentry" achieving an impressive 92.65% accuracy in vulnerability detection, surpassing existing state-of-the-art methods such as SyseVR and VulDeBERT. This novel methodology marks a paradigm shift in vulnerability detection, blending advanced AI with practical application efficiency.
- Subjects
COMPUTER security vulnerabilities; GENERATIVE pre-trained transformers; DEEP learning; CONVOLUTIONAL neural networks; LANGUAGE models
- Publication
Revista Academiei Fortelor Terestre, 2024, Vol 29, Issue 1, p98
- ISSN
1582-6384
- Publication type
Article
- DOI
10.2478/raft-2024-0010