Exploiting Large Language Models to Train Automatic Detectors of Sensitive Data.
Simone De RenzisDennis DossoAlberto TestolinPublished in: IRCDL (2024)
Keyphrases
- language model
- sensitive data
- language modeling
- n gram
- probabilistic model
- privacy preserving
- document retrieval
- data storage
- speech recognition
- language modelling
- context sensitive
- information retrieval
- smart card
- test collection
- query expansion
- retrieval model
- relevance model
- third party
- sensitive information
- statistical language models
- information security
- document ranking
- malicious users
- privacy protection
- language models for information retrieval
- smoothing methods