Olympus: Sensor Privacy through Utility Aware Obfuscation
By Nisarg Raval, Ashwin Machanavajjhala, Jerry Pan. 2018
48 citations recorded by the source corpus.
Abstract Personal data garnered from various sensors are often offloaded by applications to the cloud for analytics. This leads to a potential risk of disclosing private user information. We observe that the analytics run on the cloud are often limited to a machine learning model such as predicting a user’s activity using an activity classifier. We present Olympus, a privacy framework that limits the risk of disclosing private user information by obfuscating sensor data while minimally affecting the functionality the data are intended for. Olympus achieves privacy by designing a utility aware obfuscation mechanism, where privacy and utility requirements are modeled as adversarial networks. By rigorous and comprehensive evaluation on a real world app and on benchmark datasets, we show that Olympus successfully limits the disclosure of private information without significantly affecting functionality of the application.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Abhishek Singh
- Praneeth Vepakomma
- Ramesh Raskar
- Fatemehsadat Mirshghallah
- Mohammad Malekzadeh
- Richard G. Clegg
- Mohammadkazem Taram
- Andrea Cavallaro
Citations in the corpus
- Privacy in Deep Learning: A Survey (2020, methodology): “R-100 Image Classification w/ DNN Shredder [31] # # # SVHN, VGG-Face, ImageNet Classification w/ DNN Sensor Data Obfuscation [142] # # # Iphone 6s Accelerometer Data Activity Recognition w/ DNN Olympus [143] # # # Driving images Activity Recognition w/ DNN DPFE [29] # # # CelebA Image Classification w/”
- Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels (2021, unknown): “The goal of this term is to drive the discriminator to predict randomly uniform outputs (Raval et al., 2019).”
- Mobile sensor data anonymization (2018, background): “Considering the decoder’s output leads to a more reliable data protection [20, 26].”
- Privacy and Utility Preserving Sensor-Data Transformations (2019, background): “Local mech-4 anisms, instead, manipulate data at the user side, without relying on a trusted curator [26, 29, 30].”