ethz-spylab

rlhf_trojan_competition

Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

rlhf-poisoning

Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"

diffusion_denoised_smoothing

Certified robustness "for free" using off-the-shelf diffusion models and classifiers

robust-style-mimicry

superhuman-ai-consistency

satml-llm-ctf

Code used to run the platform for the LLM CTF colocated with SaTML 2024

realistic-adv-examples

Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]

lm_memorization_data

Data for "Quantifying Memorization Across Neural Language Models"

lm-extraction-benchmark-data

Datasets for the SATML 2023 competition on training data extraction

misleading-privacy-evals

Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)

infoseclab_23

.github

data-decay

Playing around with the CC3M data

llm_lab

privacy

Library for training machine learning models with privacy for training data

ctf-satml24-data-analysis