Conventions used

There are a number of text conventions used throughout this book.

Code in text: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "Next, we can adversarially train the model by first initializing a new KerasClassifier with the robust_model."

A block of code is set as follows:

base_classifier = KerasClassifier(model=base_model,\                                  clip_values=(min_, max_))y_test_mdsample_prob = np.max(y_test_prob[sampl_md_idxs],\                                                       axis=1)y_test_smsample_prob = np.max(y_test_prob[sampl_sm_idxs],\                                                       axis=1)

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

robust_classifier = KerasClassifier(model=robust_model,\                                    clip_values=(min_, max_))attacks = BasicIterativeMethod(robust_classifier, eps=0.3,\                               eps_step=0.01, max_iter=20)trainer = AdversarialTrainer(robust_classifier, attacks, ratio=0.5)trainer.fit(X_train, ohe.transform(y_train), nb_epochs=30,\            batch_size=128)

Any command-line input or output is written as follows:

$ mkdir css
$ cd css

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "Select System info from the Administration panel."

Tips or important notes

Appear like this.