SRI Lab, ETH Zurich

lmql

A language for constraint-guided and efficient LLM programming.

silq

securify2

Securify v2.0

UnuglifyJS

A simpler open-source version of JavaScript deobfuscator JSNice

language-model-arithmetic

Controlled Text Generation via Language Model Arithmetic

psi

Exact Inference Engine for Probabilistic Programs

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.

zkay

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

sven

ChatProtect

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

llmprivacy

eth-sri.github.io

SRI Group Website

tableak

TabLeak: Tabular Data Leakage in Federated Learning

mn-bab

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

Delta-Siege

watermark-stealing

Watermark Stealing in Large Language Models

automated-error-analysis

Automated Classification of Model Errors on ImageNet (NeurIPS 2023)

SafeCoder

fairness-feedback-nlp

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

malicious-contamination

fare

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

abstraqt

ChromeER

synthetiq

TAPS

privacy-inference-multimodal

watermark-stealing-website

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

progsyn

datamin

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

ibp-propagation-tightness