| Autor: |
Xiaoyu Yi, Gaolei Li, Jianhua Li, Ao Ding |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Applied Sciences, Vol 14, Iss 11, p 4502 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2076-3417 |
| DOI: |
10.3390/app14114502 |
| Popis: |
To enhance the security of vehicular software systems, inversely identifying the underlying function types of binary files plays a key role in threat discovery. However, existing function-type inference (FTI) methods can only provide a suboptimal performance because of splitting binary files into multiple sub-blocks as inputs, which results in breaking the program context logic and complete data dependency. To solve this problem, we propose a novel representation-fused function-type inference (RepFTI) framework for secure vehicular software systems. First, the RepFTI learns semantic representations of assembly codes and then extracts node representations in the function call graph by the multi-head attention mechanism of Graph-Attention Transformer (GAT) models. Second, the RepFTI fuses these representations to accurately infer the function type. With RepFTI, the specific limits of in-vehicle software will be bypassed, which proposes a promising direction for other work that relies on reverse engineering to improve software security. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
