Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper explores the application of transformer models to detect software vulnerabilities in C/C++ code, addressing the limitations of previous deep learning approaches in capturing global contextual information. They use program slices containing syntactic and semantic features, such as API calls and pointer manipulations, as input to the transformer. Experiments demonstrate that the transformer-based approach can accurately identify vulnerabilities with moderate resource usage and training time, enhanced by data balancing and hyperparameter tuning.
Transformers can spot software bugs better than previous deep learning methods, thanks to their knack for understanding the big picture of code.
Detecting software vulnerabilities is critical to ensuring the security and reliability of modern computer systems. Deep neural networks have shown promising results on vulnerability detection, but they lack the capability to capture global contextual information on vulnerable code. To address this limitation, we explore the application of transformers for C/C++ vulnerability detection. We use program slices that encapsulate key syntactic and semantic features of program code, such as API function calls, array usage, pointer manipulations, and arithmetic expressions. By leveraging transformers'capability to capture both local and global contextual information on vulnerable code, our work can identify vulnerabilities accurately. Combined with data balancing and hyperparameter fine-tuning, our work offers a robust and efficient approach to identifying vulnerable code with moderate resource usage and training time.