Secure Storage and Privacy-Preserving Scanpath Comparison via Garbled Circuits in Eye Tracking

2026-04-21

AI Summary

This work addresses the lack of privacy protection in existing scanpath comparison methods for eye-tracking, which hinders their secure deployment in real-world scenarios. It introduces garbled circuits to this domain for the first time, enabling secure computation of MultiMatch, ScanMatch, and SubsMatch similarity measures in the encrypted domain under the semi-honest security model. The proposed framework supports both two-party collaborative computation and a server-aided architecture with offline data owners, ensuring end-to-end input privacy without any leakage of intermediate or final results. Experimental evaluation on three eye-tracking datasets demonstrates that the method achieves near-identical accuracy to plaintext computation while maintaining practical runtime and communication overhead, thereby offering a viable balance between strong security guarantees and real-world applicability.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Multi-modal Vision
• Search and Optimization: Distributed Search

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

With the growing use of eye tracking on VR and mobile platforms, gaze data is increasing. While scanpath comparison is important to gaze behavior analysis, existing methods lack privacy-preserving capabilities for real-world use. We present a garbled-circuit (GC)-based approach enabling secure storage and privacy-preserving scanpath comparison under the semi-honest model. It supports two configurations: (1) a two-party setting where the data owner and processor jointly compute similarity scores without revealing their inputs, and (2) a server-assisted setting where encrypted scanpaths are stored and processed while the data owner remains offline. All decryption and comparison operations are executed inside the GC. Experiments on three eye-tracking datasets evaluate fidelity, runtime, and communication, and show secure results for MultiMatch, ScanMatch, and SubsMatch closely match plaintext outcomes, with manageable runtime and communication overhead. Tests under various network conditions indicate that the design remains feasible for real-world privacy-preserving scanpath analysis and can be extended to other GC-based behavioral algorithms.

Problem

• privacy-preserving
• scanpath comparison
• eye tracking
• secure computation
• gaze data

Innovation

• garbled circuits
• privacy-preserving
• scanpath comparison
• secure computation
• eye tracking