Jan Dubiński

Jan Dubiński

PhD Student @ Warsaw University of Technology. AI Safety / Trustworthy ML / Generative Models

Posts by Tags

Image Autoregressive Models

Image AutoRegressive Models Leak More Training Data Than Diffusion Models

less than 1 minute read

Published:

Image AutoRegressive models (IARs) have recently emerged as a powerful alternative to diffusion models (DMs), surpassing them in image generation quality, speed, and scalability. Yet, despite their advantages, the privacy risks of IARs remain completely unexplored. When trained on sensitive or copyrighted data, these models may unintentionally expose training samples, creating major security and ethical concerns.

membership inference

Image AutoRegressive Models Leak More Training Data Than Diffusion Models

less than 1 minute read

Published:

Image AutoRegressive models (IARs) have recently emerged as a powerful alternative to diffusion models (DMs), surpassing them in image generation quality, speed, and scalability. Yet, despite their advantages, the privacy risks of IARs remain completely unexplored. When trained on sensitive or copyrighted data, these models may unintentionally expose training samples, creating major security and ethical concerns.

privacy attacks

Image AutoRegressive Models Leak More Training Data Than Diffusion Models

less than 1 minute read

Published:

Image AutoRegressive models (IARs) have recently emerged as a powerful alternative to diffusion models (DMs), surpassing them in image generation quality, speed, and scalability. Yet, despite their advantages, the privacy risks of IARs remain completely unexplored. When trained on sensitive or copyrighted data, these models may unintentionally expose training samples, creating major security and ethical concerns.