Skip to main content

Scan AI models for problems

Project description

AI Scan

This is a scanner that will scan your AI models for problems. Currently it focuses on bias testing. It is currently pre-alpha.

How to Use

First install it:

pip install aiscan

Run it in this manner (currently supports models from HuggingFace’s repository):

aiscan --huggingface roberta-base --task fill-mask

Here is another example with a different bias task.

aiscan --huggingface cross-encoder/nli-distilroberta-base --task zero-shot-classification

That’s it for now. More will come.

Future Work

  • More bias tests. More metrics for bias testing based on the research in the field.

  • Integration with other types of testing (eg. adversarial robustness)

  • More kinds of models besides HuggingFace models. We are especially interested in MLFlow integration.

  • Documentation.

Please contribute if you can. Help is always helpful.

License

Apache

Credit

A project of IQT Labs.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aiscan-0.1.0.tar.gz (4.1 kB view details)

Uploaded Source

Built Distribution

aiscan-0.1.0-py2.py3-none-any.whl (8.6 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file aiscan-0.1.0.tar.gz.

File metadata

  • Download URL: aiscan-0.1.0.tar.gz
  • Upload date:
  • Size: 4.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.13

File hashes

Hashes for aiscan-0.1.0.tar.gz
Algorithm Hash digest
SHA256 678f2da6ebc3d7f6ef0b3d3b5c321cfbbcba268560cd7f321882f8fd78103023
MD5 12e422ab81d27e6654efbd7c49191ce5
BLAKE2b-256 5f406558efad0647e68548bbf45de2210908d241ef13d18c9015c0770e4db6a8

See more details on using hashes here.

File details

Details for the file aiscan-0.1.0-py2.py3-none-any.whl.

File metadata

  • Download URL: aiscan-0.1.0-py2.py3-none-any.whl
  • Upload date:
  • Size: 8.6 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.13

File hashes

Hashes for aiscan-0.1.0-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 b45ed5dfa0027dccb42a8cd60ee234039ebf384043c8dd4ad02e4a8f6b45da96
MD5 a6536da34e7a455fa6368edb23c3b43e
BLAKE2b-256 9640321f0d3dcf580d75aaa231c7ae2faffdc816a7c779ab8c9c6b04d4c4a3dc

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page