Summary of Dream: Domain-free Reverse Engineering Attributes Of Black-box Model, by Rongqing Li et al.
DREAM: Domain-free Reverse Engineering Attributes of Black-box Model
by Rongqing Li, Jiaqi Yu, Changsheng Li, Wenhan Luo, Ye Yuan, Guoren Wang
First submitted to arxiv on: 20 Jul 2023
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 This paper presents a solution to the problem of attributing black-box neural networks without requiring access to their training datasets. Traditional methods rely on knowing the dataset used for training, which is often not feasible in real-world scenarios. The researchers propose a framework called DREAM (Domain-agnostic Reverse Engineering Attributes of Models) that uses out-of-distribution generalization to infer the attributes of a target black-box model without prior knowledge of its training data. This approach allows for robust and domain-agnostic model attribute reverse engineering, with strong generalization ability. To validate their method, the authors conducted extensive experiments, demonstrating superior performance compared to existing baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A group of researchers tried to figure out how to tell what makes a mysterious AI model tick without having access to its original training data. Usually, you need that information to understand a model’s secrets, but it’s not always available. The team developed a new approach called DREAM that can still learn about the model’s characteristics even if we don’t know where it came from. They tested their method and found it worked better than other ways of doing things. |
Keywords
* Artificial intelligence * Generalization
