huihun/Gencoding
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Qian Feng 2016-12-16 19:38:10 -05:00 committed by GitHub
parent 0c699a829e
commit 7aca23f5d2
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -1,13 +1,18 @@
This project provides two components of Genius, a graph-based bug search framework. The first component is the raw feature extraction. The second is the online bug search engine. This project provides two components of Genius, a graph-based bug search framework. The first component is the raw feature extraction. The second is the online bug search engine.
1. The raw feature extraction is designed to achieve following two goals: 1. The raw feature extraction is designed to achieve following two goals:
-> Extract the control flow graph for each binary function -> Extract the control flow graph for each binary function
-> Extract the attributes for each node in the grap -> Extract the attributes for each node in the grap
The feature extraction is built on top of IDA-pro. We wrote the scripts based on ida-python and extract the attributed control flow graph. The feature extraction is built on top of IDA-pro. We wrote the scripts based on ida-python and extract the attributed control flow graph.
2. The online bug search engine is used for real-time search: 2. The online bug search engine is used for real-time search:
-> It utilized localality sensitive hashing for indexing -> It utilized localality sensitive hashing for indexing
-> Nearest-neighbor search algorithm for search -> Nearest-neighbor search algorithm for search
The online search is based on nearpy (https://github.com/pixelogik/NearPy). The online search is based on nearpy (https://github.com/pixelogik/NearPy).