Summary of Embedding Attack Project (work Report), by Jiameng Pu and Zafar Takhirov
Embedding Attack Project (Work Report)
by Jiameng Pu, Zafar Takhirov
First submitted to arxiv on: 24 Jan 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 This paper presents a comprehensive summary of the Membership Inference Attacks (MIA) conducted by the Embedding Attack Project, covering threat models, experimental setup, results, findings, and discussion. The report evaluates two primary MIA strategies on 6 AI models spanning Computer Vision to Language Modelling. Additionally, it touches on ongoing experiments exploring MIA defense and neighborhood-comparison embedding attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how hackers can try to figure out if a computer program is using certain information or not. The authors tested different ways hackers might do this and saw what happened when they used six different AI models. They’re also working on finding ways to stop these hacks and trying new ideas like comparing the similarities between data points. |
Keywords
* Artificial intelligence * Embedding * Inference
