SRI Lab, ETH Zurich

eth-sri.github.io

SRI Group Website

sven

constat.github.io

ConStat

A statistical test for contamination detection in language models.

cuts

lmql

A language for constraint-guided and efficient LLM programming.

language-model-arithmetic

Controlled Text Generation via Language Model Arithmetic

fairness-feedback-nlp

Human-Guided Fair Classification for NLP (ICLR 2023, Spotlight)

ChatProtect

This is the code for the paper "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation".

mn-bab

[ICLR 2022] Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound

privacy-inference-multimodal

watermark-stealing-website

The website for "Watermark Stealing in Large Language Models".

ChromeER

dl2

DL2 is a framework that allows training neural networks with logical constraints over numerical values in the network (e.g. inputs, outputs, weights) and to query networks for inputs fulfilling a logical formula.

llmprivacy

datamin

This is the Repository containing the implementation of our paper "From Principle to Practice: Vertical Data Minimization for Machine Learning".

watermark-stealing

Watermark Stealing in Large Language Models

synthetiq

SafeCoder

ibp-propagation-tightness

silq

malicious-contamination

Delta-Siege

automated-error-analysis

Automated Classification of Model Errors on ImageNet (NeurIPS 2023)

zkay

A programming language and compiler which enable automatic compilation of intuitive data privacy specifications to NIZK-enabled private smart contracts.

fare

FARE: Provably Fair Representation Learning with Practical Certificates (ICML '23)

securify2

Securify v2.0

UnuglifyJS

A simpler open-source version of JavaScript deobfuscator JSNice

TAPS

tableak

TabLeak: Tabular Data Leakage in Federated Learning