2020
DOI: 10.1016/j.cose.2020.102032
|View full text |Cite
|
Sign up to set email alerts
|

FIT: Inspect vulnerabilities in cross-architecture firmware by deep learning and bipartite matching

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
1
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 17 publications
(9 citation statements)
references
References 7 publications
0
9
0
Order By: Relevance
“…FIT [24] considers the function level statistical features, the basic block level statistical features and the assembly instructions. It utilizes word2vec and structure2vec to generate function embeddings.…”
Section: Baselinesmentioning
confidence: 99%
See 3 more Smart Citations
“…FIT [24] considers the function level statistical features, the basic block level statistical features and the assembly instructions. It utilizes word2vec and structure2vec to generate function embeddings.…”
Section: Baselinesmentioning
confidence: 99%
“…Recently, several studies [10,11,24,28,35,37,39] apply deep learning in binary analysis. They leverage control flow graphs or assembly instructions as input, and use neural network to learn semantic embeddings which are then used to detect binary code similarity across architectures and/or optimization levels.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…Recently, deep learning technology has achieved promising improvements in intelligent program analysis. To improve the effectiveness and efficiency of the binary similarity comparison task, researchers pay attention to learning-based approaches [10,13,23,46,50,28,15,31,8,30,48,26,9]. α-diff exploited the siamese-CNN network to achieve cross-version binary code similarity detection.…”
Section: Learning-based Binary Similarity Comparison Approachesmentioning
confidence: 99%