Semantics-Preserved Distortion for Personal Privacy Protection in Information Management
Not on the map. Why?
Abstract (arXiv)
In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive information from raw texts, this paper suggests a more linguistically-grounded approach to distort texts while maintaining semantic integrity. To this end, we leverage Neighboring Distribution Divergence, a novel metric to assess the preservation of semantic meaning during distortion. Building on this metric, we present two distinct frameworks for semantic-preserving distortion: a generative approach and a substitutive approach. Our evaluations across various tasks, including named entity recognition, constituency parsing, and machine reading comprehension, affirm the plausibility and efficacy of our distortion technique in personal privacy protection. We also test our method against attribute attacks in three privacy-focused assignments within the NLP domain, and the findings underscore the simplicity and efficacy of our data-based improvement approach over structural improvement approaches. Moreover, we explore privacy protection in a specific medical information management scenario, showing our method effectively limits sensitive data memorization, underscoring its practicality.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 80 references that are in the map. First posted on arXiv 4 Jan 2022.
Builds on
28 of 80 references.
References · 28
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2019Publicly Available Clinical BERT Embeddingscited by 1,002
- 2018CoQA: A Conversational Question Answering Challengecited by 683
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
16 more
- 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
- 2020Named Entity Recognition as Dependency Parsingcited by 151
- 2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
- 2019Semantics-aware BERT for Language Understandingcited by 112
- 2021Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?cited by 93
- 2020Retrospective Reader for Machine Reading Comprehensioncited by 86
- 2020Fast and Accurate Neural CRF Constituency Parsingcited by 50
- 2021Graph Embedding for Recommendation against Attribute Inference Attackscited by 40
- 2021Undistillable: Making A Nasty Teacher That CANNOT teach studentscited by 36
- 2018SDNet: Contextualized Attention-based Deep Network for Conversational Question Answeringcited by 30
- 2018Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learningcited by 28
- 2021Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIscited by 18
- 2018Stochastic Answer Networks for SQuAD 2.0cited by 5
- 2019Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modellingcited by 4
- 2021Contextualized Semantic Distance between Highly Overlapped Textscited by 2
- 2017Towards a More Reliable Privacy-preserving Recommender Systemcited by 1
Built on by
Not cited yet.