From Here to Provtopia

Pasquier, Thomas; Eyers, David; Seltzer, Margo

doi:10.1007/978-3-030-33752-0_4

Cited by 4 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compliance with privacy regulations to prevent attacks has also gained interest, and many approaches have been developed to suggest solutions [18][19][20][21][22][23][24]. Challenges and opportunities for genomics data sharing is explored in [25].…”

Section: Privacy Attacks Toward Machine Learning Models Related Workmentioning

confidence: 99%

Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology

Yoon

Stanley

Christian

et al. 2022

CBM

View full text Add to dashboard Cite

BACKGROUND: With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. OBJECTIVE: The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The objective of the study is to quantify the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients’ information to mitigate confidentiality breaches. METHODS: The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. RESULTS: The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance.

show abstract

Section: Privacy Attacks Toward Machine Learning Models Related Workmentioning

confidence: 99%

Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology

Yoon

Stanley

Christian

et al. 2022

CBM

View full text Add to dashboard Cite

show abstract

“…More recent applications of provenance include its use in system security, including visualization and explanation of software faults, intrusion detection, and compliance with regulations involving protection of personal data. 7 A thorough review of these topics will be part of a future paper in Patterns , and all packages discussed are available from https://end-to-end-provenance.github.io/ .…”

Section: Main Textmentioning

confidence: 99%