Summary of Byzantine-robust Federated Learning: An Overview with Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols, by Atharv Deshmukh
Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
by Atharv Deshmukh
First submitted to arxiv on: 30 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
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 paper presents an exhaustive taxonomy of existing methods and frameworks for preventing Byzantine attacks in Federated Learning (FL) paradigms. The study focuses on the Robustness of Federated Learning (RoFL) protocol, analyzing its strengths and weaknesses, before proposing two novel Sybil-based attacks that exploit RoFL vulnerabilities. The paper concludes with proposals for future testing, implementation details, and directions for improving the RoFL protocol and Byzantine-robust frameworks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how to keep machine learning models safe when many people work together on private data. Some bad guys might try to make the model worse by secretly adding bad information. The researchers group all the ways to stop this from happening into categories, then look closely at one method called RoFL. They find some weaknesses in RoFL and suggest two new tricks that can be used to take advantage of these weaknesses. Finally, they give ideas for how to test and improve RoFL and other methods like it. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
