3 papers
cs.CR2025
FedPoP: Federated Learning Meets Proof of Participation
Devriş İşler, Elina van Kempen, Seoyeon Hwang +1
Federated learning (FL) offers privacy preserving, distributed machine learning, allowing clients to contribute to a global model without revealing their local data. As models incr…
cs.CR2023
FreqyWM: Frequency Watermarking for the New Data Economy
Devriş İşler, Elisa Cabana, Alvaro Garcia-Recuero +2
We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership righ…
cs.CR2023
Puppy: A Publicly Verifiable Watermarking Protocol
Devriş İşler, Seoyeon Hwang, Yoshimichi Nakatsuka +2
In this paper, we propose Puppy, the first formally defined framework for converting any symmetric watermarking into a publicly verifiable one. Puppy allows anyone to verify a wate…