PuRe Adversarial Defence

This repository provides a minimal, single-file implementation of PuRe (Purified Representation).

📢 News

[July 2025] Our paper, "Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal," has been accepted to TACL 2025!

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
README.md		README.md
modeling_bert.py		modeling_bert.py
pure.py		pure.py