Summary of Enhancing Transferability Of Adversarial Attacks with Ge-advgan+: a Comprehensive Framework For Gradient Editing, by Zhibo Jin et al.
Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing
by Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Chenyu Zhang, Jiahao Huang, Jianlong Zhou, Fang Chen
First submitted to arxiv on: 22 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 framework, called GE-AdvGAN+, for transferable adversarial attacks on deep neural networks. The method integrates multiple attack strategies to enhance transferability while reducing computational costs. Compared to the baseline AdvGAN, the best-performing variant, GE-AdvGAN++, achieves an average ASR improvement of 47.8 and outperforms competing algorithms like GE-AdvGAN with an average ASR increase of 5.9. The framework also exhibits enhanced computational efficiency, achieving 2217.7 FPS. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Transferable adversarial attacks are a significant threat to deep neural networks, especially in black-box scenarios where internal model information is inaccessible. This paper proposes GE-AdvGAN+, a novel framework for transferable adversarial attacks that integrates multiple attack strategies while reducing computational costs. The method uses generative models like GANs to generate samples without retraining after an initial training phase. |
Keywords
» Artificial intelligence » Transferability
