A collection of resources on attacks and defenses targeting text-to-image diffusion models

[ICML 2024] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

cuVS - a library for vector search and clustering on the GPU

100+ Chinese Word Vectors 上百种预训练中文词向量

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Stable Diffusion without the safety filter and invisible watermark

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

A curated list of Awesome Makeup Transfer resources

Training data extraction on GPT-2

Interact with your documents using the power of GPT, 100% privately, no data leaks

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

LLMDet is a text detection tool that can identify which generated sources the text came from (e.g. large language model or human-write).

A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles

Awesome Machine Unlearning (A Survey of Machine Unlearning)

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

Directed Greybox Fuzzing with AFL

A curated list of awesome directed fuzzing research papers

FuzzBench - Fuzzer benchmarking as a service.

A self-hosted Fuzzing-As-A-Service platform

The fuzzer afl++ is afl with community patches, qemu 5.1 upgrade, collision-free coverage, enhanced laf-intel & redqueen, AFLfast++ power schedules, MOpt mutators, unicorn_mode, and a lot more!

Datasets used in the StreamSpot experiments

Runtime Security Enforcement System. Workload hardening/sandboxing and implementing least-permissive policies made easy leveraging LSMs (BPF-LSM, AppArmor).

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

PEASS - Privilege Escalation Awesome Scripts SUITE (with colors)