angelicatong/hybrid_binary_svd

A Hybrid Binary Static Vulnerability Detection. Decompile by retdec

hybrid_binary_SVD

A Hybrid Binary Static Vulnerability Detection. Decompile by retdec

file tree:

• cfgdetect   :   the GCN model to detect vulnerability

• main.ipynb   :   train & test the GCN model
• gendata.py   :   generate data to model
• main.py   :   no use

• w2v   :   use gensim to generate w2vmodel used to present token in 256bit vector

• model_out   :   store the w2v model. imported in gendata.py
• token_out   :   store the token.txt used to generate w2v model
• dot2token.py   :   load and tokenlize .dot file, output in token_out
• word2vec.py   :   load token.txt and generate w2v model
• scrap.py   :   notice that good .dot files is more than bad .dot files. So scrap.py is used to match num of both

• decompile   :   use "retdec" to decompile .c or .cpp file

• dec_cwe.py   :   decompile .c or .cpp file, output = [ .dot file | .dc file | .dsm file ] in "CWExx_good" or "CWExx_bad" floder
• scrap.py   :   remove the useless files generated by the "retdec"