Detects AI generated code using ML
Project description
BotSniffer
Detects source code generated by AI on projects using Machine Learning and "Feature Extraction."
Usage
On the command line
You can use botsniffer in your terminal as command line. You need to train the tool before being able to detect code.
I included some AI generated snippets, but you need to incorporate a bigger dataset in order to make it fully functional.
$ pip3 install botsniffer
$ botsniffer ./ --train (will train using the code in the current directory. Any files with "ai" in the name will be taken as AI generated).
$ botsniffer ./ --identify (will list feature extraction scores plus AI as True/False)
## Notice
This tool does not provide legal advice; I'm not a lawyer.
The code is an experimental implementation. Refrain from relying on the accuracy of the output of this tool.
## Contributing
Contributions are very welcome! See [CONTRIBUTING](CONTRIBUTING.md) for more info.
## License
This code is licensed under the [Apache 2.0 License](LICENSE).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
botsniffer-0.1.tar.gz
(12.4 kB
view details)
Built Distribution
botsniffer-0.1-py3-none-any.whl
(14.2 kB
view details)
File details
Details for the file botsniffer-0.1.tar.gz
.
File metadata
- Download URL: botsniffer-0.1.tar.gz
- Upload date:
- Size: 12.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 944522e614d5240493daea5cbc4b0b3b5c9cd334fa545b3777fb8c2f6ed0445c |
|
MD5 | 3c51f847d793093a8f57058226e8a6c1 |
|
BLAKE2b-256 | 734e5d88a2451bf71a666a9af2051e57e0f8992f598e9671554616f22fefeafc |
File details
Details for the file botsniffer-0.1-py3-none-any.whl
.
File metadata
- Download URL: botsniffer-0.1-py3-none-any.whl
- Upload date:
- Size: 14.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ded83c45b61046e59cf7558034bb88957d7d000915ce4c5d5f57aa00d463f959 |
|
MD5 | 48638ea28dee309e61d338ea9a3674a9 |
|
BLAKE2b-256 | 871dcb63ea7b3d263c23b45a4169d52749ad418fe8c976a228e864b7fa558f5b |