Skip to content

@adverML Adversarial Machine Learning

Change the repository type filter

All

    Repositories list

    62 repositories

    • synthesizing_robust_adversarial

      Public
      PyTorch implementation of Expectation over Transformation
      Jupyter Notebook
      •
      MIT License
      •0•13•1•0•Updated Jul 18, 2025Jul 18, 2025

    • AdvOpenOOD

      Public
      accepted at ICMLw '24
      oodadversarial-machine-learningadversarial-examplesood-detection
      Python
      •
      MIT License
      •0•1•0•0•Updated May 20, 2025May 20, 2025

    • OpenOOD

      Public
      Benchmarking Generalized Out-of-Distribution Detection
      Python
      •
      MIT License
      •153•0•0•0•Updated Mar 25, 2025Mar 25, 2025

    • I-FSJ

      Public
      Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
      Jupyter Notebook
      •
      MIT License
      •10•0•0•0•Updated Jan 11, 2025Jan 11, 2025

    • MALT

      Public
      MALT is a attack method utilizing pre-attack targeting method to speed up and improve the state of the art AutoAttack. Fully presented in the paper. the paper
      Python
      •1•0•0•0•Updated Aug 4, 2024Aug 4, 2024

    • backdoor-toolbox

      Public
      A compact toolbox for backdoor attacks and defenses.
      Python
      •23•0•0•0•Updated Jul 16, 2024Jul 16, 2024

    • foolbox

      Public
      A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
      Python
      •
      MIT License
      •433•0•0•0•Updated Apr 3, 2024Apr 3, 2024

    • vim

      Public
      Official repository for CVPR2022 publication, ViM: Out-Of-Distribution with Virtual-logit Matching
      Python
      •
      Apache License 2.0
      •13•0•0•0•Updated Mar 19, 2024Mar 19, 2024

    • RGD

      Public
      Python
      •
      GNU Lesser General Public License v3.0
      •1•0•0•0•Updated Jan 7, 2024Jan 7, 2024

    • DiffAttack

      Public
      An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.
      Python
      •
      Apache License 2.0
      •16•0•0•0•Updated Nov 30, 2023Nov 30, 2023

    • BlackboxBench

      Public
      Python
      •
      Other
      •18•1•0•0•Updated Nov 12, 2023Nov 12, 2023

    • competence_estimation

      Public
      Jupyter Notebook
      •
      MIT License
      •1•0•0•0•Updated Nov 8, 2023Nov 8, 2023

    • multiLID

      Public
      Jupyter Notebook
      •0•2•0•0•Updated Nov 4, 2023Nov 4, 2023

    • auto-attack

      Public
      Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
      Python
      •
      MIT License
      •120•1•0•0•Updated Oct 13, 2023Oct 13, 2023

    • SpectralDefense

      Public
      Python
      •0•1•0•0•Updated Oct 9, 2023Oct 9, 2023

    • GuidedDiffusionPur

      Public
      Python
      •4•0•0•0•Updated Aug 10, 2023Aug 10, 2023

    • DiffPure

      Public
      A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.
      Python
      •
      Other
      •35•0•0•0•Updated Jul 28, 2023Jul 28, 2023

    • AdversarialAttacks

      Public
      Python
      •4•0•0•0•Updated Jul 8, 2023Jul 8, 2023

    • fast-DiT

      Public
      Improved PyTorch Implementation of "Scalable Diffusion Models with Transformers"
      Python
      •
      Other
      •114•0•0•0•Updated Jun 12, 2023Jun 12, 2023

    • denoising-diffusion-pytorch

      Public
      Implementation of Denoising Diffusion Probabilistic Model in Pytorch
      Python
      •
      MIT License
      •1.2k•0•0•0•Updated Mar 29, 2023Mar 29, 2023

    • vp-for-adversarial-robustness

      Public
      Visual Prompting for Adversarial Robustness
      Python
      •4•2•0•0•Updated Jan 21, 2023Jan 21, 2023

    • tf_to_pytorch_model

      Public
      Convert tensorflow model to pytorch model via [MMdnn](https://github.com/microsoft/MMdnn) for adversarial attacks.
      Python
      •9•0•0•0•Updated Dec 1, 2022Dec 1, 2022

    • denoising-diffusion-flax

      Public
      Implementing the Denoising Diffusion Probabilistic Model in Flax
      Jupyter Notebook
      •
      Apache License 2.0
      •26•0•0•0•Updated Nov 1, 2022Nov 1, 2022

    • pytorch-ddpm-cifar10

      Public
      Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models
      Python
      •
      Do What The F*ck You Want To Public License
      •76•0•0•0•Updated Oct 12, 2022Oct 12, 2022

    • evaluating-adaptive-test-time-defenses

      Public
      Python
      •
      Apache License 2.0
      •2•0•0•0•Updated Sep 16, 2022Sep 16, 2022

    • cutmix

      Public
      a Ready-to-use PyTorch Extension of Unofficial CutMix Implementations with more improved performance.
      Python
      •
      MIT License
      •29•0•0•0•Updated Sep 6, 2022Sep 6, 2022

    • adversarialattackspytorch

      Public
      PyTorch implementation of adversarial attacks.
      Python
      •
      MIT License
      •364•0•0•0•Updated Jul 17, 2022Jul 17, 2022

    • robustness

      Public
      A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
      Jupyter Notebook
      •
      MIT License
      •182•0•0•0•Updated Jul 10, 2022Jul 10, 2022

    • visual_prompting

      Public
      Exploring Visual Prompts for Adapting Large-Scale Models
      Python
      •
      MIT License
      •33•0•0•0•Updated Jun 15, 2022Jun 15, 2022

    • SpectralDef_Framework

      Public
      Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
      adversarial-examplesadversarial-defensedeep-learningpytorch
      Python
      •
      GNU Affero General Public License v3.0
      •3•11•1•0•Updated May 12, 2022May 12, 2022