Summary of Adaptive Pruning with Module Robustness Sensitivity: Balancing Compression and Robustness, by Lincen Bai et al.
Adaptive Pruning with Module Robustness Sensitivity: Balancing Compression and Robustness
by Lincen Bai, Hedi Tabia, Raúl Santos-Rodríguez
First submitted to arxiv on: 19 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 The paper introduces Module Robustness Sensitivity (MRS), a novel metric that quantifies layer-wise sensitivity to adversarial perturbations and dynamically informs pruning decisions. Leveraging MRS, the authors propose Module Robust Pruning and Fine-Tuning (MRPF), an adaptive pruning algorithm compatible with any adversarial training method. This approach significantly enhances adversarial robustness while maintaining competitive accuracy and computational efficiency. The paper conducts extensive experiments on SVHN, CIFAR, and Tiny-ImageNet across diverse architectures, including ResNet, VGG, and MobileViT. MRPF consistently outperforms state-of-the-art structured pruning methods in balancing robustness, accuracy, and compression. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding a way to make artificial intelligence models better at defending against fake or manipulated data. The authors created a new method called Module Robust Pruning and Fine-Tuning (MRPF) that helps keep the model accurate while also making it harder for bad guys to trick it. They tested this method on different types of images and found that it worked well, making the AI models more reliable. |
Keywords
* Artificial intelligence * Fine tuning * Pruning * Resnet
