Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.
Jingwei YiYueqi XieBin ZhuKeegan HinesEmre KicimanGuangzhong SunXing XieFangzhao WuPublished in: CoRR (2023)
Keyphrases
- language model
- injection attacks
- recommender systems
- language modeling
- collaborative recommender systems
- document retrieval
- information retrieval
- n gram
- probabilistic model
- test collection
- speech recognition
- query expansion
- retrieval model
- language modelling
- statistical language models
- query terms
- smoothing methods
- language models for information retrieval
- ddos attacks
- data mining
- sql injection
- information systems
- document ranking
- relevance model
- pseudo relevance feedback
- bayesian networks
- retrieval systems