Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models.
Shuai ZhaoJinming WenLuu Anh TuanJunbo ZhaoJie FuPublished in: CoRR (2023)
Keyphrases
- language model
- attack graphs
- language modeling
- attack graph
- n gram
- penetration testing
- buffer overflow
- probabilistic model
- document retrieval
- security vulnerabilities
- information retrieval
- speech recognition
- language modelling
- query expansion
- test collection
- retrieval model
- statistical language models
- ad hoc information retrieval
- context sensitive
- document ranking
- translation model
- word error rate
- query terms
- vector space model
- language models for information retrieval
- passage retrieval
- retrieval effectiveness
- okapi bm
- language modeling approaches
- language model for information retrieval