The paper compares four audit methods for assessing identity‑level differential privacy in pre‑trained, black‑box face generators. Each method—GaussMech, KDE‑LR, MMD‑TV, and ROC‑HT—has distinct assumptions, hyperparameters, and finite‑sample limitations, and they produce markedly different epsilon estimates when applied to FaceFusion and InstantID. The study finds that all methods reveal significant identity distinguishability, but none can be reliably ranked in this high‑distinguishability regime, suggesting that future work should evaluate them on partially private mechanisms.
By Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah, Naimul Haque, Shuangqing Wei, George T. Amariucai
The paper investigates how different gaze data representations affect privacy and utility in extended reality (XR) systems. Three representations—raw gaze, spatial attention heatmaps, and engineered eye‑movement features—are compared using the HoloAssist dataset, evaluating action recognition accuracy and closed‑set user re‑identification. Engineered features preserve about 85% of action‑recognition performance while reducing re‑identification risk by roughly an order of magnitude, yet still leave some identity leakage, indicating that abstraction alone does not guarantee privacy.
By Cory Ilo, Brendan-David John, Doug A. Bowman
arXiv:2608.28691v1 Announce Type: cross
Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
By Zhimin Li, Pan Wang, Jingxian Chen, Yuantao Tang, Anthony Chen, Qian Lou, Jingtong Hu
arXiv:2608. 08977v1 Announce Type: cross Abstract: This work focuses on the impact and detection of clear contact lenses in the context of iris recognition.
By Parisa Farmanifard, Arun Ross
arXiv:2607. 25926v1 Announce Type: cross Abstract: Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for downstream tasks.
By Hui Wei, Hao Yu, Guoying Zhao
arXiv:2607. 17504v1 Announce Type: cross Abstract: Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers.
By Zhihan Ren, Lijun He, Xinyao Wang, Xinzhu Fu, Fan Li
arXiv:2608. 15614v1 Announce Type: cross Abstract: The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget.
By Matteo Stoiber, Niels Buus Lassen
arXiv:2608. 16236v1 Announce Type: new Abstract: Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, and the server completes the computation.
By Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek
arXiv:2608.23012v1 Announce Type: new
Abstract: Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion...
By Francesco Vultaggio, Predrag Djindjic, Markus Gerke, Sebastian Tschiatschek, Phillipp Fanta-Jende
Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers. Existing privacy-preserving face recognition methods mainly aim to resist unauthorized reconstruction, typically producing features whose inversion yields visibly degraded results, which may reveal the existence of protection and motivate adaptive attacks.
arXiv:2608. 08947v1 Announce Type: cross Abstract: Current hazard detection systems in autonomous driving may develop mesa objectives, learned internal goals that achieve high training performance through spurious correlations rather than genuine hazard recognition.
By Lennox Anderson, Ahmed Boutar, Jonah Mulcrone, Tal Erez
arXiv:2409. 01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models.
By Viet-Hung Tran, Ngoc-Bao Nguyen, Son T. Mai, Hans Vandierendonck, Ira Assent, Alex Kot, Ngai-Man Cheung