Update README.md
Browse files
README.md
CHANGED
|
@@ -52,7 +52,7 @@ For a finetuned ARM64BERT model, please refer to the [other model](https://huggi
|
|
| 52 |
## Data
|
| 53 |
### What data was used for training and evaluation?
|
| 54 |
The dataset is created in the same way as Wang et al. created Binary Corp.
|
| 55 |
-
A large set of
|
| 56 |
All this code is split into functions that are compiled with different optimalizations
|
| 57 |
(`O0`, `O1`, `O2`, `O3` and `Os`) and security settings (fortify or no-fortify).
|
| 58 |
This results in a maximum of 10 (5×2) different functions which are semantically similar, i.e. they represent the same functionality, but have different machine code.
|
|
|
|
| 52 |
## Data
|
| 53 |
### What data was used for training and evaluation?
|
| 54 |
The dataset is created in the same way as Wang et al. created Binary Corp.
|
| 55 |
+
A large set of source code comes from the [ArchLinux official repositories](https://archlinux.org/packages/) and the [ArchLinux user repositories](https://aur.archlinux.org/packages/).
|
| 56 |
All this code is split into functions that are compiled with different optimalizations
|
| 57 |
(`O0`, `O1`, `O2`, `O3` and `Os`) and security settings (fortify or no-fortify).
|
| 58 |
This results in a maximum of 10 (5×2) different functions which are semantically similar, i.e. they represent the same functionality, but have different machine code.
|