Jul 2026· International Journal of Computer Vision· Vol 134· 0 citations· 62 references
Computer Science
TL;DR
The two key modules of DecentDP are a parameter selector that designates a subset of parameters for local-only updates, allowing them to be updated without DP noise, and a noise injector that adaptively adds less DP noise to exchangeable parameters that are more sensitive to DP noise.
Federated learning combined with differential privacy offers a practical way to train image-analysis models on distributed camera and sensor networks. This combination is most often implemented through DP-SGD, and it avoids centralizing raw visual data. This mini review examines differentially private federated learnin...
Namrata Pandya, Dhrupa Mistry· Frontiers in Imaging· 0 citations
The concept of Federated Learning (FL) allows training models in a decentralized way without distributing raw data but, nonetheless, the gradients are vulnerable to privacy attacks that include gradient inversion, reconstruction, and membership inference. Differential Privacy (DP) is broadly used to address these risks...
Vajjakeshavulu Anusha, Ranjeeth Kumar M· 2026 International Conferenc...· 0 citations
Federated learning (FL) trains a shared model across data holders that cannot pool their records, but deployments remain bounded by three coupled costs: uplink traffic from repeated model exchange, accuracy loss under statistically heterogeneous clients, and the information that updates still leak. These are usually at...
Harshavardhan Peddireddy, Sandeep Kumar Gadde, Prasad Bheemavarapu et al.· 2026 International Conferenc...· 0 citations
Current research on Audio Deepfake Detection (ADD) mainly relies on centralized training paradigms, while paying limited attention to privacy preservation under data localization regulations or user-consent constraints. In real-world scenarios, centralized data sharing may expose sensitive user information and hinder t...
Cunhang Fan, Zhi-Qiang Tang, Jun Xue et al.· IEEE Transactions on Audio,...· 0 citations
Gradient leakage attacks have shown that an honest-but-curious server in federated learning (FL) can reconstruct private training samples directly from the gradients transmitted by clients. The original Deep Leakage from Gradients (DLG) attack, however, suffers from several optimization pathologies: the layer-wise magn...
Kai-Hong Lei· 2026 7th International Confe...· 0 citations
SplittingFed-DP relocates the Gaussian DP mechanism from the high-dimensional gradient to the low-dimensional activation space at the cut layer, audited under Rényi differential privacy and proves that this same Gaussian release coincides with the randomised-smoothing operator of Cohen et al. at the cut layer.
Rguibi Arjdal, Y. Asimi, Ahmed Asimi et al.· EPJ Web of Conferences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
