3 papers
cs.CV2026
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
Xuemei Jia, Jiawei Du, Hui Wei +3
High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. Thi…
cs.CV2026
Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan +5
Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to prese…
cs.CV2024
Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models
Yuanwei Liu, Chengyu Jia, Ruqi Xiao +4
The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges: (1) existing methods are typically effective only on specific face recognition…