|
..
|
|
adaptive_defence_evaluations
|
|
adversarial_patch
|
|
art_evaluations
|
|
hidden_trigger_backdoor
|
|
adversarial_action_recognition.ipynb
|
|
adversarial_audio_examples.ipynb
|
|
adversarial_retraining.ipynb
|
|
adversarial_training_mnist.ipynb
|
|
art-for-tensorflow-v2-callable.ipynb
|
|
art-for-tensorflow-v2-keras.ipynb
|
|
asr_deepspeech_examples.ipynb
|
|
attack_attribute_inference.ipynb
|
|
attack_attribute_inference_regressor.ipynb
|
|
attack_database_reconstruction.ipynb
|
|
attack_decision_based_boundary.ipynb
|
|
attack_decision_tree.ipynb
|
|
attack_defence_imagenet.ipynb
|
|
attack_feature_adversaries_pytorch.ipynb
|
|
attack_feature_adversaries_tensorflow_v2.ipynb
|
|
attack_graphite_blackbox.ipynb
|
|
attack_graphite_whitebox.ipynb
|
|
attack_hopskipjump.ipynb
|
|
attack_laser.ipynb
|
|
attack_membership_inference.ipynb
|
|
attack_membership_inference_regressor.ipynb
|
|
attack_membership_inference_shadow_models.ipynb
|
|
backdoor_attack_DGM.ipynb
|
|
certification_deepz.ipynb
|
|
certification_interval_domain.ipynb
|
|
certified_adversarial_training.ipynb
|
|
classifier_blackbox.ipynb
|
|
classifier_blackbox_lookup_table.ipynb
|
|
classifier_blackbox_tesseract.ipynb
|
|
classifier_catboost.ipynb
|
|
classifier_gpy_gaussian_process.ipynb
|
|
classifier_lightgbm.ipynb
|
|
classifier_scikitlearn_AdaBoostClassifier.ipynb
|
|
classifier_scikitlearn_BaggingClassifier.ipynb
|
|
classifier_scikitlearn_DecisionTreeClassifier.ipynb
|
|
classifier_scikitlearn_ExtraTreesClassifier.ipynb
|
|
classifier_scikitlearn_GradientBoostingClassifier.ipynb
|
|
classifier_scikitlearn_LogisticRegression.ipynb
|
|
classifier_scikitlearn_RandomForestClassifier.ipynb
|
|
classifier_scikitlearn_SVC_LinearSVC.ipynb
|
|
classifier_scikitlearn_pipeline_pca_cv_svc.ipynb
|
|
classifier_xgboost.ipynb
|
|
detection_adversarial_samples_cifar10.ipynb
|
|
expectation_over_transformation_classification_rotation.ipynb
|
|
fabric_for_deep_learning_adversarial_samples_fashion_mnist.ipynb
|
|
imperceptible_attack_on_tabular_data.ipynb
|
|
label_only_membership_inference.ipynb
|
|
model-stealing-demo.ipynb
|
|
model_inversion_attacks_mnist.ipynb
|
|
output_randomized_smoothing_mnist.ipynb
|
|
poisoning_attack_backdoor_audio.ipynb
|
|
poisoning_attack_backdoor_image.ipynb
|
|
poisoning_attack_bullseye_polytope.ipynb
|
|
poisoning_attack_clean_label_backdoor.ipynb
|
|
poisoning_attack_embedding.ipynb
|
|
poisoning_attack_feature_collision-pytorch.ipynb
|
|
poisoning_attack_feature_collision.ipynb
|
|
poisoning_attack_sleeper_agent.ipynb
|
|
poisoning_attack_sleeper_agent_pytorch.ipynb
|
|
poisoning_attack_svm.ipynb
|
|
poisoning_attack_witches_brew.ipynb
|
|
poisoning_attack_witches_brew_pytorch.ipynb
|
|
poisoning_defence_strip.ipynb
|
|
poisoning_defense_activation_clustering.ipynb
|
|
poisoning_defense_deep_partition_aggregation.ipynb
|
|
poisoning_defense_dp_instahide.ipynb
|
|
poisoning_defense_neural_cleanse.ipynb
|
|
poisoning_defense_spectral_signatures.ipynb
|
|
provenance_defence.ipynb
|
|
robustness_verification_clique_method_tree_ensembles_gradient_boosted_decision_trees_classifiers.ipynb
|
|
README.md
|
|
trigger_10.png
|
