Implementations of data poisoning attacks against neural networks and related defenses.
☆105Jul 16, 2024Updated last year
Alternatives and similar repositories for data-poisoning
Users that are interested in data-poisoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A unified benchmark problem for data poisoning attacks☆162Oct 4, 2023Updated 2 years ago
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆112Aug 19, 2024Updated last year
- ☆26Dec 14, 2021Updated 4 years ago
- ☆24Jan 27, 2022Updated 4 years ago
- ☆54Sep 11, 2021Updated 4 years ago
- ☆69Feb 17, 2024Updated 2 years ago
- A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)☆287Jan 11, 2025Updated last year
- Pytorch ImageNet1k Loader with Bounding Boxes.☆13Jan 23, 2022Updated 4 years ago
- ☆16Jul 17, 2022Updated 3 years ago
- Craft poisoned data using MetaPoison☆54Apr 5, 2021Updated 4 years ago
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆54Nov 29, 2021Updated 4 years ago
- APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)☆46Apr 15, 2025Updated 11 months ago
- ☆23Sep 21, 2022Updated 3 years ago
- ☆10Oct 31, 2022Updated 3 years ago
- A simple and efficient baseline for data attribution☆11Nov 10, 2023Updated 2 years ago
- ☆18Oct 12, 2022Updated 3 years ago
- Code for Data Poisoning Attacks Against Federated Learning Systems☆206Jun 13, 2021Updated 4 years ago
- ☆19Jun 5, 2023Updated 2 years ago
- Codes for the ICLR 2022 paper: Trigger Hunting with a Topological Prior for Trojan Detection☆11Sep 19, 2023Updated 2 years ago
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆73Apr 16, 2024Updated last year
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆136Nov 11, 2024Updated last year
- ☆10Jul 28, 2022Updated 3 years ago
- Pytorch Datasets for Easy-To-Hard☆29Jan 9, 2025Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆30Jul 11, 2023Updated 2 years ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆69Feb 5, 2024Updated 2 years ago
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆128Jan 18, 2022Updated 4 years ago
- ☆15Jan 16, 2024Updated 2 years ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Sep 9, 2024Updated last year
- A centralized place for deep thinking code and experiments☆90Aug 9, 2023Updated 2 years ago
- Implementation of experiments from The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning☆17May 14, 2023Updated 2 years ago
- Code for the IEEE S&P 2018 paper 'Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning'☆55Mar 24, 2021Updated 5 years ago
- ☆16Dec 3, 2021Updated 4 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆132Oct 24, 2023Updated 2 years ago
- KNN Defense Against Clean Label Poisoning Attacks☆13Sep 24, 2021Updated 4 years ago
- Official implementation of GOAT model (ICML2023)☆38Jul 3, 2023Updated 2 years ago
- Understanding Catastrophic Overfitting in Single-step Adversarial Training [AAAI 2021]☆28Jun 27, 2022Updated 3 years ago
- The official TensorFlow implementation for ICLR'22 Spotlight paper 'Responsible Disclosure of Generative Models Using Scalable Fingerprin…☆33Apr 16, 2023Updated 2 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆32Jan 9, 2022Updated 4 years ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Nov 27, 2023Updated 2 years ago