3 papers
cs.CV2026
DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition
Zhihan Ren, Lijun He, Xinyao Wang +2
Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers.…
cs.CV2025
What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
Zhihan Ren, Lijun He, Jiaxi Liang +3
Split DNNs enable edge devices by offloading intensive computation to a cloud server, but this paradigm exposes privacy vulnerabilities, as the intermediate features can be exploit…
cs.CV2024
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Andrew Westbury, Lorenzo Torresani +98
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric…