๐
๐
Old Age
Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions
June 12, 2023 ยท Entered Twilight ยท ๐ arXiv.org
Repo contents: .gitignore, LICENSE, __init__.py, attacks, configs, data, eval, misc, models, notebooks, readme.md, scripts
Authors
Harshitha Machiraju, Michael H. Herzog, Pascal Frossard
arXiv ID
2306.07178
Category
cs.CV: Computer Vision
Cross-listed
cs.AI,
cs.CR,
cs.LG
Citations
0
Venue
arXiv.org
Repository
https://github.com/code-Assasin/MUFIACode
โญ 3
Last Checked
3 months ago
Abstract
Deep learning models often face challenges when handling real-world image corruptions. In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling such corruptions. However, these datasets have a significant limitation: they do not account for all corruptions encountered in real-life scenarios. To address this gap, we present MUFIA (Multiplicative Filter Attack), an algorithm designed to identify the specific types of corruptions that can cause models to fail. Our algorithm identifies the combination of image frequency components that render a model susceptible to misclassification while preserving the semantic similarity to the original image. We find that even state-of-the-art models trained to be robust against known common corruptions struggle against the low visibility-based corruptions crafted by MUFIA. This highlights the need for more comprehensive approaches to enhance model robustness against a wider range of real-world image corruptions.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
๐
๐
Old Age
Fast R-CNN
๐
๐
Old Age