Summary of Trustworthy Machine Learning Under Social and Adversarial Data Sources, by Han Shao
Trustworthy Machine Learning under Social and Adversarial Data Sources
by Han Shao
First submitted to arxiv on: 2 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
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 research paper investigates the interactions between humans and machine learning systems, highlighting how human behaviors can impact the performance and outputs of these systems. The authors note that as machine learning permeates daily life, individuals and organizations exhibit a wide range of social and adversarial behaviors, which may affect the data used to train models. This includes strategic data generation by individuals, self-interested data collection, and potential poisoning by attackers. The study aims to address these challenges, emphasizing the need for robust machine learning systems that can handle various types of human behavior. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning is getting better at doing things like recognizing pictures and understanding speech. But how do people affect this technology? When humans interact with machine learning systems, they might behave in different ways, which could make the system work less well or even not work at all. For example, some people might try to trick the system by giving it fake information. Other people might collect data for their own purposes, which could also change how the system works. The researchers are trying to understand these interactions and find ways to make machine learning systems more robust. |
Keywords
» Artificial intelligence » Machine learning
