PurduePAML / TrojanNN
Trojan Attack on Neural Network
☆179Updated 2 years ago
Related projects: ⓘ
- Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and P…☆266Updated 4 years ago
- DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model☆206Updated 5 years ago
- ☆88Updated 3 years ago
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆47Updated 4 years ago
- TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classifica…☆274Updated last month
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆47Updated 5 years ago
- Benchmarking and Visualization Tool for Adversarial Machine Learning☆183Updated last year
- ☆133Updated 4 months ago
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆74Updated last year
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆67Updated 6 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆114Updated 10 months ago
- ☆82Updated 10 months ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆117Updated 5 months ago
- ☆60Updated 3 years ago
- Simple PyTorch implementations of Badnets on MNIST and CIFAR10.☆141Updated last year
- Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Counte…☆79Updated last year
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆115Updated 2 years ago
- Code for ML Doctor☆84Updated last month
- Implementation of membership inference and model inversion attacks, extracting training data information from an ML model. Benchmarking …☆98Updated 4 years ago
- A unified benchmark problem for data poisoning attacks☆148Updated 11 months ago
- Code for the paper "ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models"☆80Updated 2 years ago
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆29Updated 3 years ago
- Code for paper "PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking"☆62Updated 2 years ago
- ☆14Updated 2 years ago
- Knockoff Nets: Stealing Functionality of Black-Box Models☆89Updated last year
- ☆73Updated 3 years ago
- Input-aware Dynamic Backdoor Attack (NeurIPS 2020)☆27Updated last month
- Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)☆45Updated 4 years ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 3 months ago