Privacy-Preserving Machine Learning: Threats and Solutions
By Mohammad Al-Rubaie, J. M. Chang. IEEE Security and Privacy, 2018
415 citations recorded by the source corpus.
For privacy concerns to be addressed adequately in today's machine-learning (ML) systems, the knowledge gap between the ML and privacy communities must be bridged. This article aims to provide an introduction to the intersection of both fields with special emphasis on the techniques used to protect the data.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/7901981d585789369a96b6c5f5a34987ed5472a7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Timothy M. Hospedales
- Yongxin Yang
- Tao A. Xiang
- Ala Al-Fuqaha
- Sergey Levine
- Junaid Qadir
- Muhammad Bilal
- Shakir Mohamed
Citations in the corpus
- Secure and Robust Machine Learning for Healthcare: A Survey (2020, background): “The confidential data should be anonymized to prevent privacy breaches such as (re-)identification of the individuals [109].”
- A Survey of Privacy Attacks in Machine Learning (2020, background): “Some existing surveys [8, 89] provide partial coverage of privacy attacks and there are a few other peer-reviewed works on the topic [2, 47].”
- Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities (2021, background): “This will ensure that the appropriate types of protections are included in the ongoing development of AI solutions (Al-Rubaie and Chang 2019).”
- Flexible Dataset Distillation: Learn Labels Instead of Images (2020, background): “In future, label distillation could speculatively provide a useful tool for privacy preserving learning [1], e.g. in situations where organizations want to learn from user’s data.”