Alternatives and similar repositories for Black-Box-Defense:

Users that are interested in Black-Box-Defense are comparing it to the libraries listed below

• ChaojianYu / Understanding-Robust-Overfitting
  Implementation for <Understanding Robust Overftting of Adversarial Training and Beyond> in ICML'22.
  ☆12Updated 2 years ago
• UCDvision / backdoor_transformer
  ☆29Updated 2 years ago
• imrahulr / hat
  Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
  ☆29Updated 2 years ago
• mo666666 / When-Adversarial-Training-Meets-Vision-Transformers
  Official implementation of "When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture" published at Neur…
  ☆32Updated 5 months ago
• VITA-Group / Backdoor-LTH
  [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…
  ☆26Updated 2 years ago
• VITA-Group / Alleviate-Robust-Overfitting
  [ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chan…
  ☆46Updated 3 years ago
• kaiwenzha / contrastive-poisoning
  [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
  ☆30Updated last year
• AI-secure / Robustness-Against-Backdoor-Attacks
  RAB: Provable Robustness Against Backdoor Attacks
  ☆39Updated last year
• whj363636 / Self-Ensemble-Adversarial-Training
  SEAT
  ☆20Updated last year
• PKU-ML / CFA
  ☆18Updated last year
• psandovalsegura / autoregressive-poisoning
  Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)
  ☆19Updated 5 months ago
• val-iisc / GAMA-GAT
  Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses, NeurIPS Spotlight 2020
  ☆26Updated 4 years ago
• DequanWang / dent
  Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
  ☆38Updated 3 years ago
• Alan-Qin / Transfer_attack_RAP
  Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)
  ☆33Updated 2 years ago
• AISafety-HKUST / Backdoor_Safety_Tuning
  Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)
  ☆25Updated 3 months ago
• BrachioLab / adversarial_prompting
  ☆53Updated last year
• dedeswim / vits-robustness-torch
  Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]
  ☆53Updated 2 years ago
• IBM / model-sanitization
  Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…
  ☆27Updated 4 years ago
• VITA-Group / Trap-and-Replace-Backdoor-Defense
  [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…
  ☆14Updated last year
• nblt / Sub-AT
  [CVPR 2022 oral] Subspace Adversarial Training
  ☆26Updated last year
• inspire-group / proxy-distributions
  [ICLR 2022 official code] Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
  ☆29Updated 2 years ago
• ShawnXYang / AccumulativeAttack
  ☆19Updated 3 years ago
• dongyp13 / memorization-AT
  ☆21Updated 2 years ago
• qizhangli / MoreBayesian-attack
  Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.
  ☆17Updated last year
• ShawnXYang / AT_HE
  ☆35Updated 4 years ago
• LijieFan / AdvCL
  [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”
  ☆48Updated 3 years ago
• hammlab / LimitsOfUDA
  Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning. (Neurips 2021)
  ☆8Updated 3 years ago
• tml-epfl / adv-training-corruptions
  On the effectiveness of adversarial training against common corruptions [UAI 2022]
  ☆30Updated 2 years ago
• fra31 / robust-finetuning
  Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"
  ☆18Updated 2 years ago
• cychomatica / One-Pixel-Shotcut
  One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks (ICLR 2023 Spotlight)
  ☆13Updated 2 years ago