Summary of Sar-ae-sfp: Sar Imagery Adversarial Example in Real Physics Domain with Target Scattering Feature Parameters, by Jiahao Cui et al.
SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters
by Jiahao Cui, Jiale Duan, Binyan Luo, Hang Cao, Wang Guo, Haifeng Li
First submitted to arxiv on: 2 Mar 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 proposes a novel method for generating realistic adversarial examples for Synthetic Aperture Radar (SAR) target recognition models. The authors develop SAR-AE-SFP-Attack, which iteratively optimizes the coherent energy accumulation of target echoes by perturbing scattering feature parameters in the three-dimensional physical domain. Compared to digital attacks, this approach shows significant improvements in attack efficiency on CNN-based and Transformer-based models, with transferability across different models and perspectives. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates fake but realistic images that can trick computer algorithms used for detecting objects from space using radar waves. The goal is to make these algorithms more vulnerable to hacking or manipulation. The scientists developed a new method to generate these fake images by tweaking the way radar waves bounce off objects, which makes it harder for computers to recognize what’s real and what’s not. |
Keywords
» Artificial intelligence » Cnn » Transferability » Transformer
