A zero-knowledge proof of training (zkPoT) enables a party to prove that they have correctly trained a committed model based on a committed dataset without revealing any additional …
BJ Chen, S Waiwitlikhit, I Stoica, D Kang - Proceedings of the Nineteenth …, 2024 - dl.acm.org
Machine learning (ML) is increasingly used behind closed systems and APIs to make important decisions. For example, social media uses ML-based recommendation algorithms …
How can a model owner prove they trained their model according to the correct specification? More importantly, how can they do so while preserving the privacy of the …
Y Fan, B Xu, L Zhang, J Song, A Zomaya, KC Li - Information Sciences, 2023 - Elsevier
Abstract Machine Learning as a Service can provide outsourced deep learning model prediction services to clients that do not have computing resources. Meanwhile, the integrity …
Machine learning has become increasingly prominent and is widely used in various applications in practice. Despite its great success, the integrity of machine learning …
H Sun, T Bai, J Li, H Zhang - Cryptology ePrint Archive, 2023 - eprint.iacr.org
The recent advancements in deep learning have brought about significant changes in various aspects of people's lives. Meanwhile, these rapid developments have raised …
As ML models have increased in capabilities and accuracy, so has the complexity of their deployments. Increasingly, ML model consumers are turning to service providers to serve …
R Zhang, J Liu, Y Ding, Z Wang, Q Wu… - 2022 IEEE Symposium …, 2022 - ieeexplore.ieee.org
In S&P 21, Jia et al. proposed a new concept/mechanism named proof-of-learning (PoL), which allows a prover to demonstrate ownership of a machine learning model by proving …
H Wang, T Hoang - arXiv preprint arXiv:2212.05428, 2022 - arxiv.org
Machine Learning as a service (MLaaS) permits resource-limited clients to access powerful data analytics services ubiquitously. Despite its merits, MLaaS poses significant concerns …