Summary of Advlogo: Adversarial Patch Attack Against Object Detectors Based on Diffusion Models, by Boming Miao et al.
AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Models
by Boming Miao, Chunxiao Li, Yao Zhu, Weixiang Sun, Zizhe Wang, Xiaoyi Wang, Chuanlong Xie
First submitted to arxiv on: 11 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 proposed framework, AdvLogo, tackles vulnerabilities in object detectors by introducing a novel patch attack from a semantic perspective. This approach leverages diffusion denoising and perturbs latent and unconditional embeddings to create adversarial subspace. The method achieves strong attack performance while maintaining high visual quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AdvLogo is a new way to make object detectors fail by creating fake images that are hard for the detector to recognize. It works by changing the underlying structure of the image, which makes it difficult for the detector to understand what’s happening in the picture. The goal is to create attacks that can fool the detector without making the image look unnatural or distorted. |
Keywords
» Artificial intelligence » Diffusion
