Adversarial Text Purification: A Large Language Model Approach for Defense

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial perturbations from the attacked inputs, aiming to restore purified samples that retain similarity to the initially attacked ones and are correctly classified by the classifier. Due to the inherent challenges associated with characterizing noise perturbations for discrete inputs, adversarial text purification has been relatively unexplored. In this paper, we investigate the …

adversarial adversarial attacks attacks cs.ai cs.cl cs.cr cs.lg defense inputs language large large language model mechanism restore retain similarity techniques text training