jagielski / manip-ml
Code for the IEEE S&P 2018 paper 'Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning'
☆52Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for manip-ml
- Implementation of membership inference and model inversion attacks, extracting training data information from an ML model. Benchmarking …☆99Updated 5 years ago
- Privacy Risks of Securing Machine Learning Models against Adversarial Examples☆44Updated 4 years ago
- Code for Machine Learning Models that Remember Too Much (in CCS 2017)☆30Updated 7 years ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆68Updated 6 years ago
- A library for running membership inference attacks against ML models☆139Updated last year
- ☆63Updated 5 years ago
- Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Counte…☆81Updated last year
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 5 years ago
- Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models☆123Updated 7 months ago
- Code for Exploiting Unintended Feature Leakage in Collaborative Learning (in Oakland 2019)☆53Updated 5 years ago
- ☆55Updated 5 years ago
- Code for "On the Trade-off between Adversarial and Backdoor Robustness" (NIPS 2020)☆16Updated 4 years ago
- Code for "Detecting Adversarial Samples from Artifacts" (Feinman et al., 2017)☆108Updated 6 years ago
- Benchmarking and Visualization Tool for Adversarial Machine Learning☆186Updated last year
- Detecting Adversarial Examples in Deep Neural Networks☆66Updated 6 years ago
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆21Updated 5 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆46Updated 6 years ago
- ☆91Updated 4 years ago
- Code corresponding to the paper "Adversarial Examples are not Easily Detected..."☆84Updated 7 years ago
- This project's goal is to evaluate the privacy leakage of differentially private machine learning models.☆129Updated last year
- ☆45Updated 5 years ago
- Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)☆187Updated 7 years ago
- simple Differential Privacy in PyTorch☆48Updated 4 years ago
- Code for "Black-box Adversarial Attacks with Limited Queries and Information" (http://arxiv.org/abs/1804.08598)☆174Updated 3 years ago
- Adversarial Examples: Attacks and Defenses for Deep Learning☆31Updated 6 years ago
- ☆25Updated 5 years ago
- Code for NIPS'2017 paper☆49Updated 4 years ago
- Code for ML Doctor☆86Updated 3 months ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- Analytic calibration for differential privacy with Gaussian perturbations☆44Updated 6 years ago