chong-z/nlp-second-order-attack
[NAACL 2021] Code for "Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation"
This project helps evaluate the reliability of natural language processing (NLP) models. It takes an existing NLP model and a dataset of text, then systematically modifies the text to identify vulnerabilities and hidden biases in the model's predictions. The output helps machine learning engineers and researchers understand how robust their NLP models truly are when faced with slight variations in input data.
No commits in the last 6 months.
Use this if you need to deeply assess the stability and fairness of your NLP models by finding subtle weaknesses that standard evaluations might miss.
Not ideal if you are looking for a tool to simply train or deploy an NLP model without needing to rigorously test its adversarial robustness or counterfactual bias.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jun 14, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/chong-z/nlp-second-order-attack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thunlp/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
thunlp/TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
jind11/TextFooler
A Model for Natural Language Attack on Text Classification and Inference
thunlp/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
thunlp/SememePSO-Attack
Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial...