Kallima: A Clean-label Framework for Textual Backdoor Attacks. (arXiv:2206.01832v1 [cs.CR])

Although Deep Neural Network (DNN) has led to unprecedented progress in
various natural language processing (NLP) tasks, research shows that deep
models are extremely vulnerable to backdoor attacks. The existing backdoor
attacks mainly inject a small number of poisoned samples into the training
dataset with the labels changed to the target one. Such mislabeled samples
would raise suspicion upon human inspection, potentially revealing the attack.
To improve the stealthiness of textual backdoor attacks, we propose the first
clean-label framework Kallima …

attacks backdoor framework