cleverhans
cleverhans copied to clipboard
cleverhans-lab
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Hello, thank you for building such a great software package. As I am very new to this package, may I ask where I can find the DeepFool and ElasticNet attacks...
cleverhans.torch.utils.clip_eta will cause GPU memory leaking for its in-place operation when param norm==2 ``` def clip_eta(eta, norm, eps): """ PyTorch implementation of the clip_eta in utils_tf. :param eta: Tensor :param...
Hi, The adversarial examples generation is always time-consuming in adversarial training. Is there a way to conduct multi-GPU generation in tensorflow2? e.g. For a batch with 128 samples using 4...
Hello, I have seen one possible bug in the tensorflow C&W2 implementation. The **targeted** parameter does not pass to function body, instead it is defined with respect to y parameter...
Feature to report/record predicted class labels when using do_eval or model_eval. The overall accuracy is reported, however, characterizing model performance on specific test data would enable insight for a problem...
Seems like this is because CarliniWagnerL2.attack takes a single instance of x? Not sure if this is intended but is there anyway to allow for multiple x to be passed...
Hi, The test `TestSPSA::test_adv_example_success_rate_linf` in `torch/tests/test_attacks.py` has an assertion bound (`self.assertLess(adv_acc, 0.5)`) that is too loose. This means potential bug in the code could still pass the original test. To...
Implemented fix to this issue: https://github.com/cleverhans-lab/cleverhans/issues/1211. The `loss_fn` used must only take 2 parameters (output and target).
***The issue tracker should only be used to report bugs or feature requests. If you are looking for support from other library users, please ask a question on [StackOverflow](https://stackoverflow.com/questions/tagged/cleverhans).*** **Describe...
Metadata
Owner
Metadata
An adversarial example library for constructing attacks, building defenses, and benchmarking both