Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems. (arXiv:2305.19607v1 [cs.CL])

Clean-label (CL) attack is a form of data poisoning attack where an adversary
modifies only the textual input of the training data, without requiring access
to the labeling function. CL attacks are relatively unexplored in NLP, as
compared to label flipping (LF) attacks, where the latter additionally requires
access to the labeling function as well. While CL attacks are more resilient to
data sanitization and manual relabeling methods than LF attacks, they often
demand as high as ten times the …

access adversarial adversary attack attacks backdoor backdoor attacks classification data data poisoning function input labeling nlp poisoning systems text training