Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers

Understand

Text classification has become widely used in various natural language processing applications like sentiment analysis.

• Current applications often use large transformer-based language models to classify input texts.
• However, there is a lack of systematic study on how much private information can be inverted when publishing models.
• In this paper, we formulate \emph{Text Revealer} -- the first model inversion attack for text reconstruction against text classification with transformers.