Differential privacy for eye-tracking data
By Ao Liu, Lirong Xia, Andrew T. Duchowski, Reynold J. Bailey, Kenneth Holmqvist, Eakta Jain. 2019
83 citations recorded by the source corpus.
As large eye-tracking datasets are created, data privacy is a pressing concern for the eye-tracking community. De-identifying data does not guarantee privacy because multiple datasets can be linked for inferences. A common belief is that aggregating individuals' data into composite representations such as heatmaps protects the individual. However, we analytically examine the privacy of (noise-free) heatmaps and show that they do not guarantee privacy. We further propose two noise mechanisms that guarantee privacy and analyze their privacy-utility tradeoff. Analysis reveals that our Gaussian noise mechanism is an elegant solution to preserve privacy for heatmaps. Our results have implications for interdisciplinary research to create differentially private mechanisms for eye tracking.
Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science
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
- Pasin Manurangsi
- Badih Ghazi
- Rasmus Pagh
- Ameya Velingker
- Ravi Kumar
- Ying Zhao
- Jinjun Chen
- Albert Cheu
In Computer Science Applications
In Sociology and Political Science
Citations in the corpus
- Private Aggregation from Fewer Anonymous Messages (2019, background): “Moreover, very recent work in eye-tracking research [22,29] study differential privacy for eye-tracking tasks, the most basic of which is the aggregation of users’ gaze maps.”
- A Survey on Differential Privacy for Unstructured Data Content (2022, methodology): “[60] customized a differential privacy model for gaze maps on eye tracking heatmaps.”