Alternatives and similar repositories for black-box-attacks

Users that are interested in black-box-attacks are comparing it to the libraries listed below

• max-andr / provable-robustness-max-linear-regions
  Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]
  ☆32Updated 5 years ago
• max-andr / cross-lipschitz
  Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]
  ☆18Updated 7 years ago
• MadryLab / adversarial_spatial
  Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.
  ☆49Updated 5 years ago
• locuslab / perturbation_learning
  Learning perturbation sets for robust machine learning
  ☆65Updated 3 years ago
• deepgenerativeclassifier / DeepBayes
  Code release for the ICML 2019 paper "Are generative classifiers more robust to adversarial attacks?"
  ☆23Updated 6 years ago
• MadryLab / spatial-pytorch
  Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).
  ☆26Updated 5 years ago
• yangarbiter / robust-local-lipschitz
  A Closer Look at Accuracy vs. Robustness
  ☆89Updated 4 years ago
• jonasrauber / linear-region-attack
  A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturb…
  ☆12Updated 4 years ago
• locuslab / robust_union
  [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.
  ☆26Updated 11 months ago
• tonyduan / rs4a
  Randomized Smoothing of All Shapes and Sizes (ICML 2020).
  ☆52Updated 4 years ago
• locuslab / projected_sinkhorn
  ☆88Updated 11 months ago
• hendrycks / pre-training
  Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
  ☆100Updated 3 years ago
• ftramer / MultiRobustness
  Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019
  ☆47Updated 2 years ago
• davidstutz / confidence-calibrated-adversarial-training
  Implementation of Confidence-Calibrated Adversarial Training (CCAT).
  ☆45Updated 4 years ago
• StephanZheng / neural-fingerprinting
  ☆29Updated 6 years ago
• davidstutz / disentangling-robustness-generalization
  CVPR'19 experiments with (on-manifold) adversarial examples.
  ☆45Updated 5 years ago
• MadryLab / DebuggableDeepNetworks
  ☆38Updated 4 years ago
• microsoft / denoised-smoothing
  Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
  ☆97Updated 4 years ago
• facebookresearch / fisher_information_loss
  This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"
  ☆50Updated 3 years ago
• singlasahil14 / barlow
  Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction
  ☆36Updated 3 years ago
• iamgroot42 / sauron
  Code for 'One Neuron to Fool Them All'
  ☆8Updated 4 years ago
• Bai-Li / STN-Code
  Code for Stability Training with Noise (STN)
  ☆22Updated 4 years ago
• ddkang / advex-uar
  Code for "Testing Robustness Against Unforeseen Adversaries"
  ☆81Updated 11 months ago
• Hadisalman / robust-verify-benchmark
  Benchmark for LP-relaxed robustness verification of ReLU-networks
  ☆41Updated 6 years ago
• tml-epfl / adv-training-corruptions
  On the effectiveness of adversarial training against common corruptions [UAI 2022]
  ☆30Updated 3 years ago
• labsix / adversarial-logit-pairing-analysis
  Analysis of Adversarial Logit Pairing
  ☆60Updated 6 years ago
• pdejorge / N-FGSM
  Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)
  ☆25Updated 2 years ago
• uds-lsv / evaluating-logit-pairing-methods
  Logit Pairing Methods Can Fool Gradient-Based Attacks [NeurIPS 2018 Workshop on Security in Machine Learning]
  ☆19Updated 6 years ago
• MadryLab / BREEDS-Benchmarks
  ☆55Updated 4 years ago
• ajiljalal / manifold-defense
  ☆21Updated 11 months ago