Summary of Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models, by Jiaqi Li et al.
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
by Jiaqi Li, Qianshan Wei, Chuanyi Zhang, Guilin Qi, Miaozeng Du, Yongrui Chen, Sheng Bi
First submitted to arxiv on: 21 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 Machine unlearning empowers individuals with the `right to be forgotten’ by removing their private or sensitive information encoded in machine learning models. The paper proposes an efficient method, Single Image Unlearning (SIU), to unlearn the visual recognition of a concept by fine-tuning a single associated image for few steps. SIU consists of two key aspects: constructing Multifaceted fine-tuning data and jointly training loss. The proposed method is evaluated on MMUBench, a new benchmark for MU in MLLMs, and experimental results show that SIU completely surpasses the performance of existing methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine unlearning lets people forget their personal information stored in machine learning models. A team developed a way to remove visual recognition of a concept by fine-tuning a single image. This method, called Single Image Unlearning (SIU), is efficient and effective. It works by constructing special data for fine-tuning and training the model with a unique loss function. The researchers tested SIU on a new benchmark and found it performs better than other methods. |
Keywords
» Artificial intelligence » Fine tuning » Loss function » Machine learning
