Summary of Tikguard: a Deep Learning Transformer-based Solution For Detecting Unsuitable Tiktok Content For Kids, by Mazen Balat et al.
TikGuard: A Deep Learning Transformer-Based Solution for Detecting Unsuitable TikTok Content for Kids
by Mazen Balat, Mahmoud Essam Gabr, Hend Bakr, Ahmed B. Zaky
First submitted to arxiv on: 1 Oct 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 The proposed TikGuard approach utilizes a transformer-based deep learning model to detect and flag inappropriate content on TikTok, specifically designed to safeguard young viewers from harmful material. The model leverages advanced video classification techniques and a curated dataset, TikHarm, achieving an accuracy of 86.7%. This significantly improves upon existing methods in similar contexts. By employing transformer models for video classification, the study demonstrates their effectiveness in this area and lays groundwork for future research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary TikGuard is a new way to keep young people safe online. It’s a special computer program that looks at videos on TikTok and decides if they’re suitable for kids or not. The program uses a big dataset of videos with labels, like “this video is okay” or “this video is not okay”. This helps the program learn what makes a good video or a bad one. When tested, TikGuard was really accurate, getting it right 86.7% of the time! This means it can help keep kids from seeing things they shouldn’t. The researchers think this could be an important step in keeping online spaces safe for everyone. |
Keywords
» Artificial intelligence » Classification » Deep learning » Transformer
