Downloads · 30 days
2
33% of all-time downloads
sealing-the-backdoor-unlearning-adversarial-triggers-in-diffusion-models
ashwath-vaithina/sealing-the-backdoor-unlearning-adversarial-triggers-in-diffusion-models
sealing-the-backdoor-unlearning-adversarial-triggers-in-diffusion-models is a text-to-image model from ashwath-vaithina. Use it when you need an image from a text prompt. It is set up for diffusers.
This repository contains the code and model weights from the work presented in the paper Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation.
All-time downloads
6
Public
Repo size
75.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors70.5 GB · 89%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Dec 12, 2024
- Updated
- Sep 4, 2025
- SHA
- 34b2c864
Model card
From the Hugging Face model README
Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
This repository contains the code and model weights from the work presented in the paper Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation.
The paper addresses the vulnerability of text-to-image diffusion models to backdoor attacks, where imperceptible textual triggers can cause manipulated outputs. The proposed approach, Self-Knowledge Distillation with Cross-Attention Guidance (SKD-CAG), selectively erases the model's learned associations between adversarial text triggers and poisoned outputs while preserving overall generation quality. SKD-CAG neutralizes backdoor influences at the attention level using knowledge distillation.
For more details and the implementation, please refer to the GitHub repository.
- Task
- Text-to-Image
- Library
- diffusers
- Created
- Dec 12, 2024
- Updated
- Sep 4, 2025