Code is not Natural Language: Unlock the Power of Semantics-Oriented Graph Representation for Binary Code Similarity Detection.
Haojie HeXingwei LinZiang WengRuijie ZhaoShuitao GanLibo ChenYuede JiJiashui WangZhi XuePublished in: USENIX Security Symposium (2024)
Keyphrases
- binary codes
- graph representation
- hamming distance
- natural language
- similarity search
- graph model
- gray code
- image collections
- hash functions
- data sets
- high dimensional data
- pattern matching
- feature space
- search engine
- distance function
- natural language processing
- object recognition
- keywords
- similarity measure
- high level
- machine learning