Alternatives and similar repositories for forensics:

Users that are interested in forensics are comparing it to the libraries listed below

• AISafety-HKUST / Backdoor_Safety_Tuning
  Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)
  ☆25Updated 2 months ago
• AI-secure / Robustness-Against-Backdoor-Attacks
  RAB: Provable Robustness Against Backdoor Attacks
  ☆39Updated last year
• zhenglisec / Label-Only-MIA
  ☆20Updated 4 months ago
• inspire-group / unlearning-verification
  verifying machine unlearning by backdooring
  ☆19Updated last year
• 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 …
  ☆18Updated last year
• Gwinhen / PixelBackdoor
  This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."
  ☆24Updated 2 years ago
• uchicago-sandlab / naturalbackdoors
  Code for identifying natural backdoors in existing image datasets.
  ☆15Updated 2 years ago
• wronnyhuang / metapoison
  Craft poisoned data using MetaPoison
  ☆49Updated 3 years ago
• cleverhans-lab / entangled-watermark
  ☆45Updated 3 years ago
• TDteach / Demon-in-the-Variant
  ☆13Updated 3 years ago
• bboylyg / RNP
  Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)
  ☆34Updated last year
• DennisLiu2022 / Membership-Inference-Attacks-by-Exploiting-Loss-Trajectory
  ☆24Updated 2 years ago
• grasses / PromptCARE
  Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.
  ☆30Updated 5 months ago
• RorschachChen / entangled-watermark-torch
  ☆17Updated 3 years ago
• TemporaryAcc0unt / composite-attack
  ☆21Updated 4 years ago
• KaiyuanZh / OrthogLinearBackdoor
  [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks
  ☆19Updated 2 weeks ago
• reds-lab / ASSET
  This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…
  ☆17Updated last year
• ShawnXYang / AccumulativeAttack
  ☆19Updated 3 years ago
• fmy266 / Pytorch-Backdoor-Unlearning
  Pytorch implementation of backdoor unlearning.
  ☆17Updated 2 years ago
• tianshuocong / TePA
  [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models
  ☆17Updated 11 months ago
• bboylyg / ABL
  Anti-Backdoor learning (NeurIPS 2021)
  ☆81Updated last year
• hkunzhe / label_consistent_attacks_pytorch
  A minimal PyTorch implementation of Label-Consistent Backdoor Attacks
  ☆29Updated 3 years ago
• jinyuan-jia / BaggingCertifyDataPoisoning
  ☆10Updated 4 years ago
• lvpeizhuo / MEA-Defender
  This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.
  ☆18Updated last year
• csdongxian / ANP_backdoor
  Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
  ☆56Updated last year
• yfchen1994 / poisoning_membership
  ☆18Updated 8 months ago
• Megum1 / DFST
  [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
  ☆28Updated 2 weeks ago
• sunbelbd / invisible_backdoor_attacks
  ☆19Updated 2 years ago
• alevine0 / DPA
  Code for the paper "Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks"
  ☆12Updated 2 years ago
• tribhuvanesh / prediction-poisoning
  Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)
  ☆29Updated 4 years ago