RIML Lab

💠 Compositional Learning Journal Club

Join us this week for an in-depth discussion on Unlearning in Deep generative models in the context of cutting-edge generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle unlearning tasks and where improvements can be made.

✅ This Week's Presentation:

🔹 Title: The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models


🔸 Presenter: Aryan Komaei

🌀 Abstract:
This paper tackles a critical issue in text-to-image diffusion models like Stable Diffusion, DALL·E, and Midjourney. These models are trained on massive datasets, often containing private or copyrighted content, which raises serious legal and ethical concerns. To address this, machine unlearning methods have emerged, aiming to remove specific information from the models. However, this paper reveals a major flaw: these unlearned concepts can come back when the model is fine-tuned. The authors introduce a new framework to analyze and evaluate the stability of current unlearning techniques and offer insights into why they often fail, paving the way for more robust future methods.

Session Details:
- 📅 Date: Tuesday
- 🕒 Time: 11:00 - 12:00 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban

We look forward to your participation! ✌️

www.tg-me.com/sa/RIML Lab/com.RIMLLab/213

1.6K viewsAmir Kasaei, edited  Jun 16 at 11:29

💠 Compositional Learning Journal Club

Join us this week for an in-depth discussion on Unlearning in Deep generative models in the context of cutting-edge generative models. We will explore recent breakthroughs and challenges, focusing on how these models handle unlearning tasks and where improvements can be made.

✅ This Week's Presentation:

🔹 Title: The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models


🔸 Presenter: Aryan Komaei

🌀 Abstract:
This paper tackles a critical issue in text-to-image diffusion models like Stable Diffusion, DALL·E, and Midjourney. These models are trained on massive datasets, often containing private or copyrighted content, which raises serious legal and ethical concerns. To address this, machine unlearning methods have emerged, aiming to remove specific information from the models. However, this paper reveals a major flaw: these unlearned concepts can come back when the model is fine-tuned. The authors introduce a new framework to analyze and evaluate the stability of current unlearning techniques and offer insights into why they often fail, paving the way for more robust future methods.

Session Details:
- 📅 Date: Tuesday
- 🕒 Time: 11:00 - 12:00 PM
- 🌐 Location: Online at vc.sharif.edu/ch/rohban

We look forward to your participation! ✌️

BY RIML Lab