Pinned Repositories
debin
Machine Learning to Deobfuscate Binaries
diffai
A certifiable defense against adversarial examples by training neural networks to be provably robust
eran
ETH Robustness Analyzer for Deep Neural Networks
ilf
AI based fuzzer based on imitation learning
language-model-arithmetic
Controlled Text Generation via Language Model Arithmetic
lmql
A language for constraint-guided and efficient LLM programming.
Nice2Predict
Learning framework for program property prediction
securify
[DEPRECATED] Security Scanner for Ethereum Smart Contracts
securify2
Securify v2.0
UnuglifyJS
A simpler open-source version of JavaScript deobfuscator JSNice
SRI Lab, ETH Zurich's Repositories
eth-sri/lmql
A language for constraint-guided and efficient LLM programming.
eth-sri/debin
Machine Learning to Deobfuscate Binaries
eth-sri/diffai
A certifiable defense against adversarial examples by training neural networks to be provably robust
eth-sri/language-model-arithmetic
Controlled Text Generation via Language Model Arithmetic
eth-sri/ilf
AI based fuzzer based on imitation learning
eth-sri/psi
Exact Inference Engine for Probabilistic Programs
eth-sri/sven
eth-sri/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.
eth-sri/fastsmt
Learning to Solve SMT Formulas Fast
eth-sri/llmprivacy
eth-sri/ChatProtect
This is the code for the paper "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation".
eth-sri/SafeCoder
eth-sri/SynthPAI
A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)
eth-sri/watermark-stealing
Watermark Stealing in Large Language Models (ICML '24)
eth-sri/learning-real-bug-detector
eth-sri/tableak
TabLeak: Tabular Data Leakage in Federated Learning
eth-sri/llm-quantization-attack
eth-sri/eth-sri.github.io
SRI Group Website
eth-sri/mn-bab
[ICLR 2022] Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
eth-sri/cuts
eth-sri/fairness-feedback-nlp
Human-Guided Fair Classification for NLP (ICLR 2023, Spotlight)
eth-sri/ConStat
A statistical test for contamination detection in language models.
eth-sri/cascade-routing
eth-sri/ChromeER
eth-sri/synthetiq
eth-sri/domino
eth-sri/exploiting-llm-quantization-website
eth-sri/watermark-stealing-website
The website for "Watermark Stealing in Large Language Models".
eth-sri/constat.github.io
eth-sri/CTBench