Summary of Adversarial Attacks on Image Classification Models: Fgsm and Patch Attacks and Their Impact, by Jaydip Sen and Subhasis Dasgupta
Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact
by Jaydip Sen, Subhasis Dasgupta
First submitted to arxiv on: 5 Jul 2023
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Cryptography and Security (cs.CR); 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 paper explores adversarial attacks on convolutional neural networks (CNNs) used for image classification tasks. Specifically, it investigates the effectiveness of two well-known attacks, fast gradient sign method (FGSM) and adversarial patch attack, against three pre-trained CNN architectures: ResNet-34, GoogleNet, and DenseNet-161. The study analyzes the impact of these attacks on image classification performance using the ImageNet dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how deep-learning models for image recognition can be tricked into making mistakes when attacked by malicious images. It shows that even very good image classification models can make a lot of errors if they’re given special “adversarial” pictures designed to fool them. The research finds out what happens to three popular image classification models, ResNet-34, GoogleNet, and DenseNet-161, when they’re shown these tricky images. |
Keywords
* Artificial intelligence * Cnn * Deep learning * Image classification * Resnet
