A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks. (arXiv:2206.08514v1 [cs.LG])

Textual backdoor attacks are a kind of practical threat to NLP systems. By
injecting a backdoor in the training phase, the adversary could control model
predictions via predefined triggers. As various attack and defense models have
been proposed, it is of great significance to perform rigorous evaluations.
However, we highlight two issues in previous backdoor learning evaluations: (1)
The differences between real-world scenarios (e.g. releasing poisoned datasets
or models) are neglected, and we argue that each scenario has its own …

backdoor benchmarks frameworks lg