tianyu139 / friendly-noise

Related projects: ⓘ

• psandovalsegura / autoregressive-poisoning
  Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)
  ☆18Updated last week
• jinghuichen / AWM
  Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)
  ☆14Updated last year
• cleverhans-lab / dataset-inference
  [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning
  ☆30Updated last year
• YuYang0901 / EPIC
  Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)
  ☆17Updated 2 years ago
• zqypku / mm_poison
  ☆16Updated 10 months ago
• reds-lab / Meta-Sift
  The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …
  ☆16Updated last year
• AISafety-HKUST / stable_backdoor_purification
  Towards Stable Backdoor Purification through Feature Shift Tuning (NeurIPS 2023)
  ☆22Updated last month
• CGCL-codes / TeCo
  The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consist…
  ☆19Updated last year
• HanxunH / CognitiveDistillation
  [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image
  ☆30Updated 2 months ago
• TDteach / Demon-in-the-Variant
  ☆12Updated 2 years ago
• liuzrcc / ImageShortcutSqueezing
  Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
  ☆11Updated 2 months ago
• bboylyg / RNP
  Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)
  ☆25Updated 8 months ago
• point0bar1 / ebm-defense
  PyTorch implementation of BPDA+EOT attack to evaluate adversarial defense with an EBM
  ☆23Updated 4 years ago
• YiZeng623 / frequency-backdoor
  ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…
  ☆38Updated 2 years ago
• whj363636 / Self-Ensemble-Adversarial-Training
  SEAT
  ☆19Updated 11 months ago
• UCDvision / backdoor_transformer
  ☆27Updated 2 years ago
• jinhaoduan / SecMI
  [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?
  ☆29Updated 2 weeks ago
• YuxinWenRick / canary-in-a-coalmine
  ☆31Updated 9 months ago
• Alan-Qin / Transfer_attack_RAP
  Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)
  ☆33Updated last year
• kong13661 / PIA
  Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
  ☆11Updated 6 months ago
• rkteddy / channel-Lipschitzness-based-pruning
  Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness
  ☆28Updated last year
• xherdan76 / A-Unified-Approach-to-Interpreting-and-Boosting-Adversarial-Transferability
  A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)
  ☆28Updated 2 years ago
• YiZeng623 / I-BAU
  Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
  ☆49Updated last year
• RU-System-Software-and-Security / UNICORN
  ☆14Updated last year
• xpf / Data-Efficient-Backdoor-Attacks
  Data-Efficient Backdoor Attacks
  ☆18Updated 2 years ago
• hannxu123 / fair_robust
  ☆10Updated 2 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,…
  ☆13Updated 9 months ago
• qizhangli / MoreBayesian-attack
  Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.
  ☆18Updated last year
• JinyiW / GuidedDiffusionPur
  ☆46Updated last year
• lhfowl / adversarial_poisons
  ☆47Updated 3 years ago