1 1

matthieu Laszlo

mlaszlo

AI & ML interests

Neural networks, Gen ai, Transformers, ssl, multimodality

Recent Activity

updated a dataset 4 days ago

mlaszlo/mrz-simpo-dataset

published a dataset 4 days ago

mlaszlo/mrz-simpo-dataset

reacted to MikeDoes's post with 👀 18 days ago

A single lock on a door isn't enough. Real security is about layers. The same is true for AI privacy. A new paper, "Whispered Tuning", offers a fantastic layered solution that aims to fortify LLMs against privacy infringements. We're proud that the first, essential layer, a high-precision PII redaction model was built on the foundation of the Ai4Privacy/pii-65k dataset. Our dataset provided the necessary training material for their initial anonymization step, which then enabled them to develop further innovations like differential privacy fine-tuning and output filtering. This is a win-win: our data helps create a solid base, and researchers build powerful, multi-stage privacy architectures on top of it. Together, we're making AI safer. 🔗 Read the full paper to see how a strong foundation enables a complete privacy solution: https://www.scirp.org/journal/paperinformation?paperid=130659 🚀 Stay updated on the latest in privacy-preserving AI—follow us on LinkedIn: https://www.linkedin.com/company/ai4privacy/posts/

View all activity

Organizations

updated a dataset 4 days ago

mlaszlo/mrz-simpo-dataset

Viewer • Updated 4 days ago • 4.99k • 25

published a dataset 4 days ago

mlaszlo/mrz-simpo-dataset

Viewer • Updated 4 days ago • 4.99k • 25

reacted to MikeDoes's post with 👀 18 days ago

Post

3742

A single lock on a door isn't enough. Real security is about layers.

The same is true for AI privacy. A new paper, "Whispered Tuning", offers a fantastic layered solution that aims to fortify LLMs against privacy infringements.

We're proud that the first, essential layer, a high-precision PII redaction model was built on the foundation of the Ai4Privacy/pii-65k dataset.

Our dataset provided the necessary training material for their initial anonymization step, which then enabled them to develop further innovations like differential privacy fine-tuning and output filtering. This is a win-win: our data helps create a solid base, and researchers build powerful, multi-stage privacy architectures on top of it.

Together, we're making AI safer.

🔗 Read the full paper to see how a strong foundation enables a complete privacy solution: https://www.scirp.org/journal/paperinformation?paperid=130659

🚀 Stay updated on the latest in privacy-preserving AI—follow us on LinkedIn: https://www.linkedin.com/company/ai4privacy/posts/