Summary of One Noise to Rule Them All: Multi-view Adversarial Attacks with Universal Perturbation, by Mehmet Ergezer and Phat Duong and Christian Green and Tommy Nguyen and Abdurrahman Zeybey
One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation
by Mehmet Ergezer, Phat Duong, Christian Green, Tommy Nguyen, Abdurrahman Zeybey
First submitted to arxiv on: 2 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- 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 introduces a novel approach to generating robust multi-view adversarial examples in 3D object recognition, operating on multiple 2D images. The method, dubbed a universal perturbation technique, enhances model scalability and robustness by bridging the gap between conventional 2D attacks and 3D-like attack capabilities. This scalable solution is suitable for real-world applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make computer vision models more reliable by creating fake examples of 3D objects that can fool them. Instead of only attacking a single view, they attack multiple views at once, making it harder to cheat the model. This makes the model more robust and prepares it for real-world use. |
