Summary of Multi-view Black-box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid, by Kalibinuer Tiliwalidi et al.
Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
by Kalibinuer Tiliwalidi, Chengyin Hu, Weiwen Shi
First submitted to arxiv on: 1 Jul 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 In this paper, researchers explore physical adversarial attacks on infrared object detectors, a crucial technology in various applications. The study focuses on developing an attack methodology called Adversarial Infrared Grid (AdvGrid) that can successfully deceive detectors in both digital and physical environments. AdvGrid uses a genetic algorithm to optimize perturbations applied to different parts of a pedestrian’s clothing to achieve multi-view attacks. The proposed method outperforms baseline approaches, achieving attack success rates of 80% in digital environments and 91.86% in physical environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this research paper investigates ways to trick infrared sensors that detect people or objects. The scientists developed a new method called AdvGrid that uses clever patterns on clothing to fool these detectors. They tested the method and found it was very good at deceiving the sensors, making it a potential threat to security. |
