Training-free Lexical Backdoor Attacks on Language Models.
Yujin HuangTerry Yue ZhuoQiongkai XuHan HuXingliang YuanChunyang ChenPublished in: WWW (2023)
Keyphrases
- language model
- language modeling
- context sensitive
- document retrieval
- speech recognition
- n gram
- probabilistic model
- language modelling
- information retrieval
- retrieval model
- statistical language models
- smoothing methods
- test collection
- query terms
- query expansion
- pseudo relevance feedback
- document ranking
- ad hoc information retrieval
- training set
- natural language processing
- vector space model
- relevance model
- retrieval effectiveness
- statistical language modeling
- term dependencies
- decision trees