Metraipolis › archive › dc_cdfd240c32f2

Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR — arXiv:2609.04592

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04592
License (as archived): CC0-1.0
Archived: 2026-10-16T22:52:24.577Z
SHA-256 of the archived text: 6a6928580de6d5b15e334be46995bc5b60d9db3305483a542543af2bf9c72a6c
Stable URL of this page: https://metraipolis.com/documento/dc_cdfd240c32f2

How to cite

Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR — arXiv:2609.04592 — arXiv (en), https://arxiv.org/abs/2609.04592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdfd240c32f2 (Metraipolis archive dc_cdfd240c32f2, sha256 6a6928580de6d5b15e334be46995bc5b60d9db3305483a542543af2bf9c72a6c)

BibTeX

@misc{dccdfd240c32f2,
  title = {Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR — arXiv:2609.04592},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04592},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdfd240c32f2; sha256 6a6928580de6d5b15e334be46995bc5b60d9db3305483a542543af2bf9c72a6c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Intelligent extended reality (XR) systems increasingly use eye and head tracking to infer user intent, task, and attention, but the same signals can also reveal biometric identity. We study whether gaze data representation choice can serve as a lightweight privacy control at feature extraction, before adding perturbation or formal privacy mechanisms. Using the egocentric HoloAssist dataset, we compare three gaze representations under matched model capacity: raw gaze, spatial attention heatmaps, and engineered eye-movement features. We evaluate each representation on action recognition as task utility and closed-set user re-identification as privacy leakage. Representation choice substantially changes the privacy-utility tradeoff. Engineered features retain roughly 85% of raw gaze's action-recognition accuracy while reducing re-identification by about an order of magnitude, to roughly four times the chance rate across 206 identities. This reduction attenuates rather than eliminates identity leakage, and the differences across representations show that abstraction alone does not guarantee privacy. Engineered features expose interpretable and auditable structure, giving designers a transparent privacy lever that complements mechanisms such as differential privacy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.HC).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Emerging Technologies (cs.ET); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.04592 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:31:08.894Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).