sakshiudeshi / Astraea
Code for "Astraea: Grammar-based Fairness Testing"
☆10Updated 3 years ago
Alternatives and similar repositories for Astraea:
Users that are interested in Astraea are comparing it to the libraries listed below
- White-box Fairness Testing through Adversarial Sampling☆13Updated 3 years ago
- Improving Machine Translation Systems via Isotopic Replacement☆11Updated last year
- SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)☆29Updated 4 years ago
- StereoSet: Measuring stereotypical bias in pretrained language models☆180Updated 2 years ago
- Code for the paper: "Adversarial Examples for Models of Code"☆17Updated 4 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆135Updated 3 months ago
- ☆27Updated 4 years ago
- Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)☆295Updated 8 months ago
- ☆9Updated 2 years ago
- Adversarial Robustness for Code☆15Updated 4 years ago
- Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)☆38Updated 5 years ago
- This repository contains the data and code introduced in the paper "CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Maske…☆115Updated last year
- Replication Package for "Natural Attack for Pre-trained Models of Code", ICSE 2022☆46Updated 7 months ago
- A collection of publications that works on code models but beyond focusing on the accuracies.☆13Updated last year
- ☆128Updated last year
- Code to reproduce data for Bias in Bios☆46Updated last year
- A framework for assessing and improving classification fairness.☆33Updated last year
- ☆9Updated 3 years ago
- ☆39Updated 5 years ago
- [ACL 2020] Towards Debiasing Sentence Representations☆64Updated 2 years ago
- Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"☆52Updated last year
- Backdooring Neural Code Search☆13Updated last year
- ☆15Updated last year
- A Diagnostic Study of Explainability Techniques for Text Classification☆66Updated 4 years ago
- Bad Characters: Imperceptible NLP Attacks☆34Updated 11 months ago
- Aequitas, a directed fairness testing framework machine learning models.☆9Updated 3 years ago
- ☆51Updated 6 years ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆47Updated 3 years ago
- VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning☆38Updated 2 years ago