13o-bbr-bbq

13o-bbr-bbq's Stars

• nomic-ai/gpt4all

  GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

  Language:C++72.8k6502.1k7.9k

• microsoft/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

  Language:Python36.5k3482.9k4.2k

• facebookresearch/fairseq

  Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

  Language:Python31.1k4214.2k6.5k

• chartist-js/chartist

  Simple responsive charts

  Language:TypeScript13.4k3311.1k2.5k

• ultralytics/yolov3

  YOLOv3 in PyTorch > ONNX > CoreML > TFLite

  Language:Python10.3k1561.8k3.5k

• qqwweee/keras-yolo3

  A Keras implementation of YOLOv3 (Tensorflow backend)

  Language:Python7.1k1977123.4k

• Trusted-AI/adversarial-robustness-toolbox

  Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

  Language:Python5.1k998961.2k

• pyauth/pyotp

  Python One-Time Password Library

  Language:Python3.1k52101333

• QData/TextAttack

  TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

  Language:Python3.1k36282412

• allanzelener/YAD2K

  YAD2K: Yet Another Darknet 2 Keras

  Language:Python2.7k91175878

• zzh8829/yolov3-tf2

  YoloV3 Implemented in Tensorflow 2.0

  Language:Jupyter Notebook2.5k75351901

• Azure/PyRIT

  The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

  Language:Python2.3k35177440

• vectara/hallucination-leaderboard

  Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

  Language:Python1.7k431965

• mitre/advmlthreatmatrix

  Adversarial Threat Landscape for AI Systems

  1.1k1084104

• DSE-MSU/DeepRobust

  A pytorch adversarial library for attack and defense methods on images and graphs

  Language:Python1k16108194

• Azure/counterfit

  a CLI that provides a generic automation layer for assessing the security of ML models

  Language:Python8403140138

• OWASP/www-project-top-10-for-large-language-model-applications

  OWASP Foundation Web Respository

  Language:TeX67688119173

• mazen160/shennina

  Automating Host Exploitation with AI

  Language:Python5321614100

• EQuiw/2019-scalingattack

  Image-Scaling Attacks and Defenses

  Language:Jupyter Notebook1804627

• neulab/RIPPLe

  Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)

  Language:Jupyter Notebook14071120

• bargavj/EvaluatingDPML

  This project's goal is to evaluate the privacy leakage of differentially private machine learning models.

  Language:Python13161048

• Lab41/cyphercat

  Implementation of membership inference and model inversion attacks, extracting training data information from an ML model. Benchmarking attacks and defenses.

  Language:Jupyter Notebook102112241

• mitre-atlas/arsenal

  CALDERA plugin for adversary emulation of AI-enabled systems

  Language:Python93229

• BishopFox/BrokenHill

  A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

  Language:Python891113

• trx14/TrojanNet

  Language:Python844523

• moohax/Proof-Pudding

  Copy cat model for Proofpoint

  Language:Python82614

• ZANSIN-sec/ZANSIN

  Language:Perl597166

• locuslab/breaking-poisoned-classifier

  Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"

  Language:Jupyter Notebook26611

• cybozu/prompt-hardener

  Prompt Hardener is a tool designed to evaluate and enhance the securify of system prompts for RAG systems.

  Language:Python1522

• definitively-not-a-lab-rat/gamin

  Language:Python3002