A Different Level Text Protection Mechanism With Differential Privacy
Qingwen Fu
TL;DR
This paper proposes a novel text protection mechanism using differential privacy that leverages BERT to assign importance levels to words, aiming to improve privacy while maintaining utility in long texts.
Contribution
It introduces a new method for text privacy protection based on word importance and differential privacy, specifically tailored for long texts, with theoretical validation.
Findings
Effective extraction of important words using BERT
Maintains text utility under differential privacy constraints
Applicable to long text privacy protection
Abstract
The article introduces a method for extracting words of different degrees of importance based on the BERT pre-training model and proves the effectiveness of this method. The article also discusses the impact of maintaining the same perturbation results for words of different importance on the overall text utility. This method can be applied to long text protection.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Rights Management and Security
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Softmax · Dropout · Layer Normalization · Linear Layer · Adam · Weight Decay · Dense Connections · WordPiece