Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
Authors:
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4561-4573
Abstract
While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders from external sources, and their users trust that the retrieved models will behave as promised. Unfortunately, this might not be the case. We introduce backdoor attacks against text-guided generative models and demonstrate that their text encoders pose a major tampering risk. Our attacks only slightly alter an encoder so that no suspicious model behavior is apparent for image generations with clean prompts. By then inserting a single character trigger into the prompt, e.g., a non-Latin character or emoji, the adversary can trigger the model to either generate images with pre-defined attributes or images following a hidden, potentially malicious description. We empirically demonstrate the high effectiveness of our attacks on Stable Diffusion and highlight that the injection process of a single backdoor takes less than two minutes. Besides phrasing our approach solely as an attack, it can also force an encoder to forget phrases related to certain concepts, such as nudity or violence, and help to make image generation safer. Our source code is available at https://github.com/LukasStruppek/Rickrolling-the-Artist.Keywords
All Related Versions
Funding Information
- Ministry of Education
This publication has 35 references indexed in Scilit:
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance2022
- Backdoor Attacks on Self-Supervised Learning2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- On Aliased Resizing and Surprising Subtleties in GAN Evaluation2022
- DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation2022
- Mitigating backdoor attacks in LSTM-based text classification systems by Backdoor Keyword IdentificationNeurocomputing, 2021
- Clean-Label Backdoor Attacks on Video Recognition Models2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- ImageNet: A large-scale hierarchical image database2009