Nicolas Papernot

Exploring how machine unlearning aids in data privacy and compliance.

Architectural backdoors pose serious security risks in neural networks, often remaining undetected.

A look at how models can perpetuate bias and impact fairness.

New methods improve privacy auditing, focusing on hidden state models in machine learning.

Examining the challenges and implications of unlearning in AI models.

This article examines risks linked to LLMs and proposes ways to enhance safety.

Discover how Artificial Dopamine mimics brain learning to enhance AI.