Summary of Learning Robust and Privacy-preserving Representations Via Information Theory, by Binghui Zhang et al.
Learning Robust and Privacy-Preserving Representations via Information Theory
by Binghui Zhang, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, Binghui Wang
First submitted to arxiv on: 15 Dec 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 In this paper, researchers propose an information-theoretic framework for learning representations that are robust to both security attacks (adversarial examples) and privacy attacks (private attribute inference). The approach aims to maintain task utility while mitigating these threats. Novel theoretical results are derived under the framework, including a trade-off between adversarial robustness/utility and attribute privacy, as well as guaranteed attribute privacy leakage against attribute inference adversaries. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making machine learning models more secure and private. It wants to make sure that models can’t be tricked into doing bad things by attackers, and also that people’s personal information stays safe. The researchers have come up with a new way of teaching machines to learn things in a way that keeps them safe from both kinds of attacks. |
Keywords
» Artificial intelligence » Inference » Machine learning
