Summary of Enhancing Remote Adversarial Patch Attacks on Face Detectors with Tiling and Scaling, by Masora Okano et al.
Enhancing Remote Adversarial Patch Attacks on Face Detectors with Tiling and Scaling
by Masora Okano, Koichi Ito, Masakatsu Nishigaki, Tetsushi Ohki
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
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 research proposes a novel approach to attacking face detectors using Remote Adversarial Patches (RAPs). Building on existing RAP methods, the study highlights unique challenges in targeting face detectors and presents solutions to overcome these issues. The proposed patch placement method and loss function demonstrate improved detection obstruction effects compared to general object detectors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper shows that it’s possible to trick face detectors by adding special patches. Face detectors are tricky because they can detect objects of different sizes, making it hard to fool them. However, the researchers found a way to create patches that are super effective at blocking face detection. The new method works better than existing methods and could have important implications for security and privacy. |
Keywords
» Artificial intelligence » Loss function
