tianshuocong

JailbreakEval

A collection of automated evaluators for assessing jailbreak attempts.

awesome-tips

LAS-AT

Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)

VLGuard

[ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

easy-bib

do-not-answer

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Adi-Red-Scene

Local Discriminative Regions for Scene Recognition (ACMMM 2018)

AI-Security-and-Privacy-Events

A curated list of academic events on AI Security & Privacy

lm-evaluation-harness

A framework for few-shot evaluation of language models.

RAI2

Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

LLMs-Finetuning-Safety

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

FigStep

Jailbreaking Large Vision-language Models via Typographic Visual Prompts

toxic-prompt

baadd

Code for Backdoor Attacks Against Dataset Distillation

cinic-10

A drop-in replacement for CIFAR-10.

TePA

[S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models

Lion

Code for "Lion: Adversarial Distillation of Proprietary Large Language Models (EMNLP 2023)"

MGTBench

Plot_Steal

MLHospital

MART

Modular Adversarial Robustness Toolkit

PyTorch_CIFAR10

Pretrained TorchVision models on CIFAR10 dataset (with weights)

TransferAttackEval

Revisiting Transferable Adversarial Images (arXiv)

Targeted-Transfer

Simple yet effective targeted transferable attack (NeurIPS 2021)

DUA

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization (CVPR 2022)

ML-Doctor

Code for ML Doctor

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡