Summary of Buster: Implanting Semantic Backdoor Into Text Encoder to Mitigate Nsfw Content Generation, by Xin Zhao et al.
Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation
by Xin Zhao, Xiaojun Chen, Yuexin Xuan, Zhendong Zhao, Xiaojun Jia, Xinfeng Li, Xiaofeng Wang
First submitted to arxiv on: 10 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed framework, called Buster, addresses concerns about Not-Safe-for-Work (NSFW) content generation in deep learning models by injecting backdoors into text encoders to prevent harmful content creation. This innovative approach leverages deep semantic information rather than explicit prompts as triggers, redirecting NSFW prompts towards targeted benign prompts. Buster also employs energy-based training data generation through Langevin dynamics for adversarial knowledge augmentation, ensuring robustness in defining harmful concepts. The framework fine-tunes text encoders of Text-to-Image models efficiently and outperforms nine state-of-the-art baselines, achieving a superior NSFW content removal rate of at least 91.2% while preserving harmless image quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Buster is a new way to stop bad images from being made on the internet. Right now, people use special tricks to make sure no naughty pictures are created, but these methods can be slow and not very good at catching all the bad stuff. Buster works differently by adding secret codes to the computer’s brain so it knows when someone is trying to make a yucky image. This helps keep the internet clean and safe for everyone. |
Keywords
» Artificial intelligence » Deep learning
