sakshiudeshi / Astraea
Code for "Astraea: Grammar-based Fairness Testing"
☆9Updated 2 years ago
Related projects: ⓘ
- Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)☆290Updated last month
- A framework for assessing and improving classification fairness.☆32Updated last year
- Natural Language Attacks in a Hard Label Black Box Setting.☆40Updated 3 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆28Updated 2 years ago
- Bad Characters: Imperceptible NLP Attacks☆33Updated 5 months ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆114Updated 11 months ago
- StereoSet: Measuring stereotypical bias in pretrained language models☆165Updated last year
- ☆9Updated 3 years ago
- [ACL 2020] Towards Debiasing Sentence Representations☆59Updated last year
- ☆101Updated last year
- ☆28Updated 3 years ago
- This repository contains the data and code introduced in the paper "CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Maske…☆97Updated 6 months ago
- To analyze and remove gender bias in coreference resolution systems☆74Updated 3 years ago
- ☆36Updated 5 years ago
- Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)☆39Updated 4 years ago
- Data for evaluating gender bias in coreference resolution systems.☆65Updated 5 years ago
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆66Updated last year
- SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)☆27Updated 3 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆53Updated 3 years ago
- Training data extraction on GPT-2☆166Updated last year
- Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)☆137Updated 3 years ago
- ☆51Updated 5 years ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆26Updated 2 years ago
- A Diagnostic Study of Explainability Techniques for Text Classification☆64Updated 3 years ago
- ☆11Updated 3 years ago
- codes for paper "learning to discriminate perturbations for blocking adversarial attacks in text classification" in EMNLP19☆15Updated 4 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆41Updated last year
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆37Updated 2 years ago
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆21Updated 2 years ago
- Papers on fairness in NLP☆421Updated 4 months ago
- Contrastive Code Representation Learning: functionality-based JavaScript embeddings through self-supervised learning☆166Updated 2 years ago