Summary of A Real-time Defense Against Object Vanishing Adversarial Patch Attacks For Object Detection in Autonomous Vehicles, by Jaden Mu
A Real-Time Defense Against Object Vanishing Adversarial Patch Attacks for Object Detection in Autonomous Vehicles
by Jaden Mu
First submitted to arxiv on: 9 Dec 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 research paper explores the vulnerability of Deep Neural Network (DNN)-based object detection models used in Autonomous Vehicles (AVs) to adversarial patches. The authors focus on object vanishing patch attacks that can cause these models to fail to detect objects, posing a significant threat to safe and trustworthy driving decisions. To address this issue, the paper presents an innovative approach to improving the robustness of DNN-based object detection models against adversarial attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Autonomous vehicles use Deep Neural Network (DNN) models for object detection in vision-based perception. The goal is to correctly detect and classify obstacles to ensure safe driving decisions. But what if someone creates a special patch that can trick the DNN model into thinking something is not there when it really is? This could be very dangerous! Researchers are trying to find ways to make these models more robust against such attacks. |
Keywords
» Artificial intelligence » Neural network » Object detection
