Are Large Pre-Trained Language Models Leaking Your Personal Information?
Jie HuangHanyin ShaoKevin Chen-Chuan ChangPublished in: EMNLP (Findings) (2022)
Keyphrases
- personal information
- language model
- pre trained
- language modeling
- third party
- training data
- sensitive information
- n gram
- information retrieval
- probabilistic model
- training examples
- social networking
- speech recognition
- query expansion
- retrieval model
- language modelling
- statistical language models
- learning algorithm
- machine learning
- small number
- image retrieval
- high dimensional
- smoothing methods