Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Title | Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks |
Publication Type | Conference Paper |
Year of Publication | 2019 |
Authors | Chen, Jiefeng, Wu, Xi, Rastogi, Vaibhav, Liang, Yingyu, Jha, Somesh |
Conference Name | 2019 IEEE European Symposium on Security and Privacy (EuroS P) |
Date Published | June 2019 |
Publisher | IEEE |
ISBN Number | 978-1-7281-1148-3 |
Keywords | adversarial attacks, Artificial neural networks, composability, cryptography, Data models, Deep Learning, image processing, ImageNet, low computational overhead, machine learning, Measurement, Metrics, MNIST, neural nets, Neural networks, Perturbation methods, pixel discretization, pixel discretization defense method, preprocessing defense, preprocessing defense methods, pubcrawl, resilience, Resiliency, Robustness, Training, white box cryptography, white-box attacks |
Abstract | Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to various systems. It is observed that such methods work well on simple datasets like MNIST, but break on more complicated ones like ImageNet under recently proposed strong white-box attacks. To understand the conditions for success and potentials for improvement, we study the pixel discretization defense method, including more sophisticated variants that take into account the properties of the dataset being discretized. Our results again show poor resistance against the strong attacks. We analyze our results in a theoretical framework and offer strong evidence that pixel discretization is unlikely to work on all but the simplest of the datasets. Furthermore, our arguments present insights why some other preprocessing defenses may be insecure. |
URL | https://ieeexplore.ieee.org/document/8806764 |
DOI | 10.1109/EuroSP.2019.00042 |
Citation Key | chen_towards_2019 |
- neural nets
- white-box attacks
- white box cryptography
- Training
- Robustness
- Resiliency
- resilience
- pubcrawl
- preprocessing defense methods
- preprocessing defense
- pixel discretization defense method
- pixel discretization
- Perturbation methods
- Neural networks
- adversarial attacks
- MNIST
- Metrics
- Measurement
- machine learning
- low computational overhead
- ImageNet
- Image Processing
- deep learning
- Data models
- Cryptography
- composability
- Artificial Neural Networks