JonasGeiping / data-poisoning
Implementations of data poisoning attacks against neural networks and related defenses.
☆81Updated 8 months ago
Alternatives and similar repositories for data-poisoning:
Users that are interested in data-poisoning are comparing it to the libraries listed below
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆101Updated 7 months ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆28Updated 4 years ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆40Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆54Updated 2 years ago
- Code for the paper: Label-Only Membership Inference Attacks☆64Updated 3 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆31Updated 3 years ago
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆53Updated 3 months ago
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆55Updated 4 months ago
- ☆65Updated last year
- Code for "Label-Consistent Backdoor Attacks"☆55Updated 4 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆82Updated last year
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆30Updated 3 years ago
- Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)☆47Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆121Updated 4 months ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆125Updated last year
- Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems☆27Updated 3 years ago
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆48Updated 2 years ago
- ☆24Updated 2 years ago
- CVPR 2021 Official repository for the Data-Free Model Extraction paper. https://arxiv.org/abs/2011.14779☆71Updated 11 months ago
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆25Updated last year
- ☆45Updated 4 years ago
- ☆45Updated 5 years ago
- Code for the paper "ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models"☆83Updated 3 years ago
- ☆26Updated 2 years ago
- Website & Documentation: https://sbaresearch.github.io/model-watermarking/☆21Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆34Updated 5 months ago
- Code for ML Doctor☆88Updated 7 months ago
- Craft poisoned data using MetaPoison☆50Updated 3 years ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆43Updated 2 years ago
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 years ago