no code implementations • 2 Apr 2024 • Alexander Nemecek, Yuzhou Jiang, Erman Ayday
In this work, focusing on the limitations of current watermarking schemes, we propose the concept of a "topic-based watermarking algorithm" for LLMs.
no code implementations • 9 Oct 2023 • Amr Abourayya, Jens Kleesiek, Kanishka Rao, Erman Ayday, Bharat Rao, Geoff Webb, Michael Kamp
Federated learning allows us to collaboratively train a model without pooling the data by iteratively aggregating the parameters of local models.
no code implementations • 4 Feb 2023 • Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday
We have evaluated the performance of AUTOLYCUS on 5 machine learning datasets, in terms of the surrogate model's accuracy and its similarity to the target model.
no code implementations • 30 Dec 2021 • Nour Almadhoun Alserr, Ozgur Ulusoy, Erman Ayday, Onur Mutlu
While sharing genomic data across researchers is an essential driver of advances in health and biomedical research, the sharing process is often infeasible due to data privacy concerns.
no code implementations • 11 Mar 2021 • Tianxi Ji, Emre Yilmaz, Erman Ayday, Pan Li
Database fingerprinting have been widely adopted to prevent unauthorized sharing of data and identify the source of data leakages.
Cryptography and Security Databases
1 code implementation • 27 Aug 2019 • Mert Bülent Sarıyıldız, Ramazan Gökberk Cinbiş, Erman Ayday
Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners.
no code implementations • ICLR 2018 • Mert Bülent Sarıyıldız, Ramazan Gökberk Cinbiş, Erman Ayday
To the best of our knowledge, the proposed approach is the first collaborative learning formulation that effectively tackles an active adversary, and, unlike model corruption or differential privacy formulations, our approach does not inherently feature a trade-off between model accuracy and data privacy.