Safeguarding Ethical AI: Detecting Potentially Sensitive Data Re-Identification and Generation of Misleading or Abusive Content from Quantized Large Language Models.
Navya Martin KollapallyJames GellerPublished in: BIOSTEC (2) (2024)
Keyphrases
- language model
- sensitive data
- language modeling
- n gram
- privacy preserving
- retrieval model
- probabilistic model
- document retrieval
- information security
- test collection
- statistical language models
- query expansion
- smart card
- data storage
- information retrieval
- sensitive information
- language modelling
- data sharing
- relevance model
- third party
- machine learning
- privacy protection
- document ranking
- smoothing methods
- database
- multimedia
- keywords
- data collection
- web documents
- data sets