CEBin introduces a novel approach to binary code similarity detection, addressing challenges in accuracy and efficiency. By fusing embedding-based and comparison-based methods, CEBin significantly improves performance in cross-architecture and cross-compiler scenarios. Experimental results demonstrate its superiority over existing state-of-the-art solutions.
CEBin's innovative design choices, such as the Reusable Embedding Cache Mechanism, contribute to its exceptional performance. The hierarchical inference process ensures efficient and accurate similarity detection in large-scale software ecosystems. Furthermore, CEBin showcases robustness across different optimization levels and architectures, highlighting its versatility and effectiveness in real-world applications.
翻譯成其他語言
從原文內容
arxiv.org
深入探究