Background Text classification models have become increasingly prevalent in cybersecurity applications, but remain susceptible to adversarial examples (e.g., carefully crafted sentences with human-unrecognizable changes to the inputs, that are misclassified). Adversarial attacks provide profound insights into the classifiers’ vulnerabilities,...

Background Adversarial purification is a defense mechanism for safe-guarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques analyze and eliminate adversarial perturbations from the attacked inputs, and help to restore purified samples that retain similarity to the attacked...