Publicly Verifiable, Private & Collaborative AI Training in a Decentralized Network May 10, 2025 @ ETHDam Yuriko Nishijima What if you don't have to reveal your personal data but you can still contribute to training a ML model? For example... Privacy-preserving recommendation system for Dapps with anonymous users Anonymous/Croudsourced heathcare data analysis platform Investors diary 📓 ⇔ liquidity of some asset X Capture the hidden trend 📈

In this post, I will leave some notes about Verifiable Federated Learning CLI Demo I have prototyped. In a nutshell, this system allows mutually distrusted parties (let's say nodes in a decentralized network like Ethereum) to privately contribute their data and collaboratively train an AI model with public verifiability. In a separate post, I will share more about my vision for this technology with some fitting use cases in my mind. Architecture Overview In my CLI demo, there are 4 parties simulated: 3 distributed clients that locally train a model on their own raw data

Publicly Verifiable, Private & Collaborative AI Training April 26, 2025 @ ZKTokyo Yuriko / X:@yurikonishijima Screenshot 2025-04-25 at 21.07.56 Screenshot 2025-04-25 at 21.26.10 Train To Earn? What if you don't have to reveal your data but still able to contribute to training a model? ->💡Federated learning + ZKP