Training-free Lexical Backdoor Attacks on Language Models. (arXiv:2302.04116v1 [cs.CR])

Large-scale language models have achieved tremendous success across various
natural language processing (NLP) applications. Nevertheless, language models
are vulnerable to backdoor attacks, which inject stealthy triggers into models
for steering them to undesirable behaviors. Most existing backdoor attacks,
such as data poisoning, require further (re)training or fine-tuning language
models to learn the intended backdoor patterns. The additional training process
however diminishes the stealthiness of the attacks, as training a language
model usually requires long optimization time, a massive amount of …

applications attacks backdoor backdoor attacks data data poisoning free inject language language models large learn natural language natural language processing nlp patterns poisoning process scale training vulnerable