SRI Lab, ETH Zurich's repositories
UnuglifyJS
A simpler open-source version of JavaScript deobfuscator JSNice
language-model-arithmetic
Controlled Text Generation via Language Model Arithmetic
ChatProtect
This is the code for the paper "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation".
eth-sri.github.io
SRI Group Website
watermark-stealing
Watermark Stealing in Large Language Models
automated-error-analysis
Automated Classification of Model Errors on ImageNet (NeurIPS 2023)
fairness-feedback-nlp
Human-Guided Fair Classification for NLP (ICLR 2023, Spotlight)
watermark-stealing-website
The website for "Watermark Stealing in Large Language Models".
datamin
This is the Repository containing the implementation of our paper "From Principle to Practice: Vertical Data Minimization for Machine Learning".