EgoPrivacy：你的第一人稱相機透露了什麼？

EgoPrivacy: What Your First-Person Camera Says About You?

June 13, 2025

作者: Yijiang Li, Genpei Zhang, Jiacheng Cheng, Yi Li, Xiaojun Shan, Dashan Gao, Jiancheng Lyu, Yuan Li, Ning Bi, Nuno Vasconcelos

cs.AI

摘要

隨著穿戴式攝影機的快速普及，關於第一人稱視角影片的隱私問題引起了廣泛關注，然而先前的研究大多忽略了對攝影機佩戴者本身的獨特隱私威脅。本研究探討了一個核心問題：從佩戴者的第一人稱視角影片中，能夠推斷出多少關於其隱私的資訊？我們引入了EgoPrivacy，這是首個用於全面評估第一人稱視覺隱私風險的大規模基準。EgoPrivacy涵蓋了三類隱私（人口統計、個人和情境），定義了七項任務，旨在從細粒度（如佩戴者身份）到粗粒度（如年齡段）恢復隱私資訊。為了進一步強調第一人稱視覺固有的隱私威脅，我們提出了檢索增強攻擊，這是一種新穎的攻擊策略，利用從外部第三人稱視角影片池中進行的第一人稱到第三人稱檢索，來提升人口統計隱私攻擊的效果。我們對所有威脅模型下可能的不同攻擊進行了廣泛比較，結果顯示佩戴者的隱私資訊極易洩露。例如，我們的研究發現表明，基礎模型即使在零樣本設置下，也能有效危及佩戴者隱私，通過恢復身份、場景、性別和種族等屬性，準確率達到70-80%。我們的代碼和數據可在https://github.com/williamium3000/ego-privacy獲取。

English

While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer. This work investigates the core question: How much privacy information about the camera wearer can be inferred from their first-person view videos? We introduce EgoPrivacy, the first large-scale benchmark for the comprehensive evaluation of privacy risks in egocentric vision. EgoPrivacy covers three types of privacy (demographic, individual, and situational), defining seven tasks that aim to recover private information ranging from fine-grained (e.g., wearer's identity) to coarse-grained (e.g., age group). To further emphasize the privacy threats inherent to egocentric vision, we propose Retrieval-Augmented Attack, a novel attack strategy that leverages ego-to-exo retrieval from an external pool of exocentric videos to boost the effectiveness of demographic privacy attacks. An extensive comparison of the different attacks possible under all threat models is presented, showing that private information of the wearer is highly susceptible to leakage. For instance, our findings indicate that foundation models can effectively compromise wearer privacy even in zero-shot settings by recovering attributes such as identity, scene, gender, and race with 70-80% accuracy. Our code and data are available at https://github.com/williamium3000/ego-privacy.