privacy
privacy copied to clipboard
tensorflow
Library for training machine learning models with privacy for training data
I am following the [blog](https://github.com/tensorflow/privacy/tree/master/tutorials/walkthrough) regarding the TF-Privacy which basically follows code from two files mnist_scratch.py and mnist_dpsgd_tutorial.py to give the overview. While mnist_scratch.py is running fine, the other file...
Shape errors linked to batch_size and num_microbatches even if `batch_size % num_microbatches == 0`
Hi, I wanted to benchmark training a model wit and without tf privacy. My problem is a modified version of MNIST classification, and so I'm only classifying numbers from 5...
I run the [`mnist_dpsgd_tutorial.py`](https://github.com/tensorflow/privacy/blob/master/tutorials/mnist_dpsgd_tutorial.py) with noise_multiplier=1.1, l2_norm_clip=1.0, batch_size=250, epochs=2, and get **the current eps 0.8** But when I run [`mnist_dpsgd_tutorial_keras.py`](https://github.com/tensorflow/privacy/blob/master/tutorials/mnist_dpsgd_tutorial_keras.py) with the same parameters, **the current eps is 16890.31**. Why...
Following the README on the [membership inference page](https://github.com/tensorflow/privacy/tree/master/tensorflow_privacy/privacy/membership_inference_attack) yields an error. I am running TensorFlow Privacy in a Google Colab notebook. After adding the module with pip through `!pip install...
I'm running into a problem and hoping you all can help. I'm using a Keras LSTM Model with tf-privacy, and when I select a num_microbatches size greater than one in...
As mentioned in https://github.com/tensorflow/privacy/pull/143#issue-524365572, the noise multiplier is an important "hyperparameter" to choose as it would affect the outcome of the target privacy budget. However due to PATE being dependent...
Unable to execute mnist_dpsgd_tutorial.py throwing a ModuleNotFoundError : **ModuleNotFoundError: No module named 'mnist_dpsgd_tutorial_common'**
Hello ! I'm getting suspicious results when computing epsilon with small alphas. For example with the code: ``` from tensorflow_privacy.privacy.analysis.rdp_accountant import compute_rdp from tensorflow_privacy.privacy.analysis.rdp_accountant import get_privacy_spent noise_multiplier = 1 batch_size...
Hello, I am currently trying to reproduce the results for training PATE on SVHN for "Scalabe Private Learning with PATE" ([Papernot et al.](https://arxiv.org/abs/1802.08908)) with the code given in `privacy/research/pate_2018`. I...
Use DPSGD in the previous mnist_dpsgd_tutorial.py There can be 90% accuracy in the file, but in mnist_dpsgd_tutorial_keras.py The medium accuracy is about 10%. I did not modify the relevant code,...
Metadata
Owner
Metadata
Library for training machine learning models with privacy for training data