Summary of Revisiting Semi-supervised Adversarial Robustness Via Noise-aware Online Robust Distillation, by Tsung-han Wu et al.
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
by Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen, Winston H. Hsu
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 paper presents SNORD, a novel framework for semi-supervised adversarial training that leverages contemporary learning techniques. Unlike prior approaches relying on robust pretrained models, SNORD introduces pseudo-label enhancement and noisy data management to achieve state-of-the-art performance across diverse datasets and labeling budgets. Without the need for pretrained models, SNORD achieves impressive robust accuracy under AutoAttack, requiring less than 0.1%, 2%, and 10% labels for CIFAR-10, CIFAR-100, and TinyImageNet-200 respectively. The paper also confirms the efficacy of each component and demonstrates the adaptability of integrating SNORD with existing adversarial pretraining strategies to further bolster robustness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to train models without needing lots of labeled data. This approach, called SNORD, uses special techniques to make the model more robust and accurate. It doesn’t require using pre-trained models, which can be helpful in certain situations. The results show that SNORD performs well across different datasets and with varying amounts of labeled data. The paper also shows how SNORD can work with other approaches to further improve robustness. |
Keywords
» Artificial intelligence » Pretraining » Semi supervised
