AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models.
Sicheng ZhuRuiyi ZhangBang AnGang WuJoe BarrowZichao WangFurong HuangAni NenkovaTong SunPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- context sensitive
- speech recognition
- test collection
- query expansion
- document retrieval
- retrieval model
- information retrieval
- ad hoc information retrieval
- statistical language models
- language modelling
- language model for information retrieval
- vector space model
- language models for information retrieval
- relevance model
- document ranking
- smoothing methods
- query terms
- text classification
- pseudo relevance feedback
- translation model
- cross lingual
- information retrieval systems
- text documents