Summary of Dream: Domain-agnostic Reverse Engineering Attributes Of Black-box Model, by Rongqing Li et al.
DREAM: Domain-agnostic 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: 8 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a novel approach to reverse-engineering deep learning models, specifically targeting black-box models deployed on machine learning platforms without access to their training datasets. The authors introduce DREAM, a general and principled framework that casts this problem as out-of-distribution (OOD) generalization. By learning a domain-agnostic meta-model, the method can infer the attributes of the target black-box model with unknown training data, exhibiting strong generalization ability. Experimental results demonstrate the superiority of the proposed method over baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a big mystery! Machine learning models are usually super tricky to understand, like black boxes. But what if we could figure out how they work without knowing what they were trained on? That’s exactly what this research does. The authors created a new way to reverse-engineer these mysterious models without needing the original training data. They called it DREAM (Domain-agnostic Reverse Engineering for Attribute Mining). It’s like solving a puzzle! This method can be used in many different areas, making it super powerful. |
Keywords
* Artificial intelligence * Deep learning * Generalization * Machine learning
