superrrpotato / Defending-Neural-Backdoors-via-Generative-Distribution-Modeling

Related projects: ⓘ

• AI-secure / Robustness-Against-Backdoor-Attacks
  RAB: Provable Robustness Against Backdoor Attacks
  ☆39Updated 11 months ago
• tribhuvanesh / prediction-poisoning
  Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)
  ☆29Updated 3 years ago
• YiZeng623 / I-BAU
  Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
  ☆49Updated last year
• SPIN-UMass / ML-Privacy-Regulization
  ☆25Updated 5 years ago
• MadryLab / backdoor_data_poisoning
  ☆25Updated 5 years ago
• shrezaei / MI-Attack
  ☆31Updated 2 weeks ago
• cchoquette / membership-inference
  Code for the paper: Label-Only Membership Inference Attacks
  ☆61Updated 3 years ago
• zhuchen03 / ConvexPolytopePosioning
  ConvexPolytopePosioning
  ☆33Updated 4 years ago
• Ping-C / certifiedpatchdefense
  Repository for Certified Defenses for Adversarial Patch ICLR-2020
  ☆32Updated 4 years ago
• lmunoz-gonzalez / Poisoning-Attacks-with-Back-gradient-Optimization
  Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"
  ☆22Updated 4 years ago
• cleverhans-lab / dataset-inference
  [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning
  ☆30Updated last year
• wronnyhuang / metapoison
  Craft poisoned data using MetaPoison
  ☆47Updated 3 years ago
• kangliucn / Fine-pruning-defense
  Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)
  ☆47Updated 5 years ago
• hkunzhe / label_consistent_attacks_pytorch
  A minimal PyTorch implementation of Label-Consistent Backdoor Attacks
  ☆25Updated 3 years ago
• sunbelbd / invisible_backdoor_attacks
  ☆19Updated 2 years ago
• samuel-yeom / ml-privacy-csf18
  Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"
  ☆38Updated 5 years ago
• csdongxian / ANP_backdoor
  Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
  ☆52Updated last year
• DingfanChen / RelaxLoss
  Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)
  ☆45Updated 2 years ago
• DennisLiu2022 / Membership-Inference-Attacks-by-Exploiting-Loss-Trajectory
  ☆23Updated last year
• MadryLab / label-consistent-backdoor-code
  Code for "Label-Consistent Backdoor Attacks"
  ☆48Updated 3 years ago
• Machine-Learning-Security-Lab / mia_prune
  Membership Inference Attacks and Defenses in Neural Network Pruning
  ☆25Updated 2 years ago
• zhenglisec / Decision-based-MIA
  ☆19Updated 2 years ago
• inspire-group / privacy-vs-robustness
  Privacy Risks of Securing Machine Learning Models against Adversarial Examples
  ☆44Updated 4 years ago
• cleverhans-lab / entangled-watermark
  ☆44Updated 3 years ago
• bboylyg / ABL
  Anti-Backdoor learning (NeurIPS 2021)
  ☆76Updated last year
• zlh-thu / StealingVerification
  Defending against Model Stealing via Verifying Embedded External Features
  ☆31Updated 2 years ago
• naiyeleo / ABS
  ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
  ☆47Updated 2 years ago
• jinyuan-jia / MemGuard
  ☆45Updated 4 years ago
• nthu-datalab / On.the.Trade-off.between.Adversarial.and.Backdoor.Robustness
  Code for "On the Trade-off between Adversarial and Backdoor Robustness" (NIPS 2020)
  ☆16Updated 3 years ago
• ShawnXYang / AccumulativeAttack
  ☆18Updated 3 years ago