binaryai / codecmr Goto Github PK

Hi,
there are only model files in this repository，could you put the source code of CodeCMR on github?

Hi, I have download the dataset of binaries. And I want to disassemble .nx files using IDA Pro.

However, I can not successfully get the control flow graph of the binaries as IDA Pro cannot figure out the binary entry point.

I am not proficient in binary analysis. So is there an automatic method to get the disassembly of these binaries?

(1, [[4, 75, 73, 78], [56, 79, 73, 83]])
features是类似这样的tuple，请问第二项当中的这些数字都是什么意思

#3 (comment)
After splitting the source code and binary into function-level pieces,how to match function level source code with binary one by one? Is it by function name? I look forward to your reply

I am confused about integer token and integer number in the paper 3.3 Code literal features. Can you explain in detail or give an example? Thanks.

The description of the dataset writes:

Each dataset has 33 columns, the first column is the source code, the other columns are the corresponding binary code on 32 combinations of different compilers (gcc/clang), different platforms (x86/x64/arm/arm64) and different optimizations (O0/O1/O2/O3).

However, the released dataset, which can be download from google cloud, seems only to have 32 binaries but no source code.

Without source code, follow-up works are hard to be carried out and compared.

Please upload the source code to help this dataset complete if possible.

您好，我在读取数据集nx文件过程中发现：g.nodes.data('raw_data'),似乎无法显示原始汇编指令文件，请问如何解析才能获得不乱码的汇编指令形式呢？
print也无法正确打印，这让我很沮丧。

请问论文所提方法的实现代码后面会开源吗？

论文中的方案中使用了character-level的DPCNN模型进行embedding表征，请问有尝试过基于word-level么？