Summary of Data Poisoning: An Overlooked Threat to Power Grid Resilience, by Nora Agah et al.
Data Poisoning: An Overlooked Threat to Power Grid Resilience
by Nora Agah, Javad Mohammadi, Alex Aved, David Ferris, Erika Ardiles Cruz, Philip Morrone
First submitted to arxiv on: 19 Jul 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 The paper explores the challenges of preserving the resilience of Dynamic Data Driven Applications Systems in the face of increasing complexity. It highlights the limitations of current optimization methods in accommodating this complexity and the growing interest in data-driven methods for operating complex systems like power grids, which makes them more vulnerable to cyberattacks. The authors focus on adversarial training and disruptions, particularly evasion and poisoning disruptions, and highlight the gap between research on these two types of disruptions when applied to the power grid. They also examine the impacts of data poisoning interventions and show how they can compromise power grid resilience. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making sure that complex systems like power grids are not disrupted by bad actors. Right now, it’s getting harder to keep these systems safe because there are more things that can go wrong, like weather events or changes in renewable energy sources. Some people have been working on ways to make the grid more secure, but they haven’t thought about all the different ways someone could try to disrupt it. The authors of this paper look at two types of disruptions: one where someone tries to make the system do something else, and another where someone adds fake information to make the system think something that isn’t true. They show that these kinds of disruptions can be a big problem for power grid resilience. |
Keywords
* Artificial intelligence * Optimization
