shizhouxing/Robustness-Verification-for-Transformers

[ICLR 2020] Code for paper "Robustness Verification for Transformers"

33
/ 100
Emerging

This tool helps machine learning engineers ensure the reliability of their Transformer models used for text classification. It takes a trained Transformer model and text datasets (like Yelp or SST-2 reviews) as input. The output specifies how robust the model is to small, imperceptible changes in the input text, helping engineers understand potential vulnerabilities.

No commits in the last 6 months.

Use this if you are a machine learning engineer working with Transformer models for natural language processing and need to formally verify their robustness against small input perturbations.

Not ideal if you need to verify the robustness of machine learning models other than Transformers or require a more general robustness verification framework.

natural-language-processing model-robustness text-classification deep-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

27

Forks

3

Language

Python

License

BSD-2-Clause

Last pushed

Nov 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/shizhouxing/Robustness-Verification-for-Transformers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.