Summary of Corrective Machine Unlearning, by Shashwat Goel et al.
Corrective Machine Unlearning
by Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal
First submitted to arxiv on: 21 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
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 Machine learning models are increasingly vulnerable to data integrity challenges due to large-scale training datasets sourced from the Internet. To address this issue, researchers investigate what model developers can do if they detect manipulated or incorrect data. This manipulation can have adverse effects like vulnerability to backdoored samples, systemic biases, and reduced accuracy on specific input domains. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning models are getting worse at doing their job because some of the training data is fake or wrong. When this happens, it’s bad news – it makes the model more likely to be tricked by bad data, biased towards certain types of information, or just not very good at working with specific kinds of input. But the problem is that all the bad data can’t always be found and fixed, so researchers are looking for ways to deal with just a small part of the affected data. |
Keywords
* Artificial intelligence * Machine learning
