Summary of Prompt-based Unifying Inference Attack on Graph Neural Networks, by Yuecen Wei et al.
Prompt-based Unifying Inference Attack on Graph Neural Networks
by Yuecen Wei, Xingcheng Fu, Lingyun Liu, Qingyun Sun, Hao Peng, Chunming Hu
First submitted to arxiv on: 20 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 In this paper, researchers propose a novel framework called ProIA (Prompt-based unifying Inference Attack) for graph neural networks (GNNs). The framework aims to enhance the predictive performance of GNNs in high-risk decision scenarios by pre-training the models using a unified prompt and introducing additional disentanglement factors. The approach retains topological information from the graph during pre-training, which improves the background knowledge of the inference attack model. ProIA demonstrates remarkable adaptability to various inference attacks through extensive experiments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNs are powerful tools for analyzing data on social networks or financial markets. But they only work well if the data is labeled correctly. One way to improve GNNs is by pre-training them using a technique called graph prompting. However, this method can be risky because it may reveal private information about individuals or companies. To address this issue, researchers have developed a new framework called ProIA that helps protect sensitive information while still improving the performance of GNNs. |
Keywords
» Artificial intelligence » Inference » Prompt » Prompting
