Summary of Query-efficient Adversarial Attack Against Vertical Federated Graph Learning, by Jinyin Chen et al.
Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning
by Jinyin Chen, Wenbo Mu, Luxin Zhang, Guohan Huang, Haibin Zheng, Yao Cheng
First submitted to arxiv on: 5 Nov 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 The proposed query-efficient hybrid adversarial attack framework, NA2, significantly improves the centralized adversarial attacks against Vertical Federated Graph Learning (VFGL) by manipulating local training data to simulate the behavior of the server model. This approach achieves state-of-the-art performance even under potential adaptive defense where the defender knows the attack method. The framework is tested on five real-world benchmarks and demonstrates robustness against various centralized attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary NA2 is a new way to make malicious attacks on graph data more effective. It does this by pretending to be one of the honest clients in a network, while secretly changing its own data to help the attack succeed. This makes it harder for the defender to detect the attack. The researchers tested NA2 with different types of attacks and found that it is very successful even when the defender knows what kind of attack is coming. |
