3 papers
cs.CR2026
Enhancing Privacy in Federated Learning via Dual Obfuscation of Gradients and Training Images
Yuki Itabashi, Hiroto Sawada, Mare Hirose +2
Federated learning enables collaborative model training while keeping data locally at each client; however, recent studies have shown that training data can be reconstructed from s…
cs.CV2026
Privacy-Preserving Semantic Segmentation without Key Management
Mare Hirose, Shoko Imaizumi, Hitoshi Kiya
This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed method, the model creator and e…
cs.CR2024
On the Security of Bitstream-level JPEG Encryption with Restart Markers
Mare Hirose, Shoko Imaizumi, Hitoshi Kiya
This paper aims to evaluate the security of a bitstream-level JPEG encryption method using restart (RST) markers, where encrypted image can keep the JPEG file format with the same…