The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Deflecting Adversarial Attacks with Pixel Deflection
Open accessAbstract
CNNs are poised to become integral parts of many critical systems. Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to cause a model to misclassify images. We present an algorithm to process an image so that classification accuracy is significantly preserved in the presence of such adversarial manipulations. Image classifiers tend to be robust to natural noise, and adversarial attacks tend to be agnostic to object location. These observations motivate our strategy, which leverages model robustness to defend against adversarial perturbations by forcing the image to match natural image statistics. Our algorithm locally corrupts the image by redistributing pixel values via a process we term pixel deflection. A subsequent wavelet-based denoising operation softens this corruption, as well as some of the adversarial changes. We demonstrate experimentally that the combination of these techniques enables the effective recovery of the true class, against a variety of robust attacks. Our results compare favorably with current state-of-the-art defenses, without requiring retraining or modifying the CNN.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Ideal spatial adaptation by wavelet shrinkage
Donoho, D. L., & Johnstone, I. M. (1994) · Biometrika · doi:10.1093/biomet/81.3.425 · Cited by 8,760
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317
Receptive fields of single neurones in the cat's striate cortex
Hubel, D. H., & Wiesel, T. N. (1959) · The Journal of Physiology · doi:10.1113/jphysiol.1959.sp006308 · Cited by 4,653
Adapting to Unknown Smoothness via Wavelet Shrinkage
Donoho, D. L., & Johnstone, I. M. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476626 · Cited by 4,630
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
Image coding using wavelet transform
Antonini, M., Barlaud, M., Mathieu, P., & Daubechies, I. (1992) · IEEE Transactions on Image Processing · doi:10.1109/83.136597 · Cited by 3,525
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Relations between the statistics of natural images and the response properties of cortical cells
Field, D. J. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.002379 · Cited by 3,241
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Papernot, N., McDaniel, P., Wu, X., Jha, S., & Swami, A. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.41 · Cited by 2,982
Adaptive wavelet thresholding for image denoising and compression
Chang, S. G., Yu, B., & Vetterli, M. (2000) · IEEE Transactions on Image Processing · doi:10.1109/83.862633 · Cited by 2,936
One Pixel Attack for Fooling Deep Neural Networks
Su, J., Vargas, D. V., & Sakurai, K. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2890858 · Cited by 2,406
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Xu, W., Evans, D., & Qi, Y. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23198 · Cited by 1,768
Understanding Neural Networks Through Deep Visualization
Yosinski, J., Clune, J., Nguyen, A. M., Fuchs, T. J., & Lipson, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06579 · Cited by 1,358
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Mathematical description of the responses of simple cortical cells*
Marĉelja, S. (1980) · Journal of the Optical Society of America · doi:10.1364/josa.70.001297 · Cited by 1,252
MagNet: A Two-Pronged Defense against Adversarial Examples
Meng, D., & Chen, H. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134057 · Cited by 1,006
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298668 · Cited by 886
Detecting Adversarial Samples from Artifacts
Feinman, R., Curtin, R. R., Shintre, S., & Gardner, A. B. (2017) · arXiv · doi:10.48550/arxiv.1703.00410 · Cited by 606
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
Huang, X., Shen, C., Boix, X., & Zhao, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.38 · Cited by 597
Spatiotemporal Elements of Macaque V1 Receptive Fields
Rust, N. C., Schwartz, O., Movshon, J. A., & Simoncelli, E. P. (2005) · Neuron · doi:10.1016/j.neuron.2005.05.021 · Cited by 457
The Space of Transferable Adversarial Examples
Tramèr, F., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03453 · Cited by 395
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
Carlini, N., & Wagner, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07263 · Cited by 307
Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples.Preprint
Papernot, N., McDaniel, P. D., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2016) · arXiv (Cornell University) · Cited by 304
Rudin-Osher-Fatemi Total Variation Denoising using Split Bregman
Getreuer, P. (2012) · Image Processing On Line · doi:10.5201/ipol.2012.g-tvd · Cited by 272
Bayesian Denoising of Visual Images in the Wavelet Domain
Simoncelli, E. P. (1999) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-0567-8_18 · Cited by 236
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Das, N., Shanbhogue, M., Chen, S.-T., Hohman, F., Chen, L., Kounavis, M. E., & Chau, D. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.02900 · Cited by 222
A study of the effect of JPG compression on adversarial images
Dziugaite, G. K., Ghahramani, Z., & Roy, D. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.00853 · Cited by 214
Defense Against Universal Adversarial Perturbations
Akhtar, N., Liu, J., & Mian, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00357 · Cited by 210
MagNet: a Two-Pronged Defense against Adversarial Examples
Meng, D., & Chen, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.09064 · Cited by 194
The Limitations of Deep Learning in Adversarial SettingsPreprint
Papernot, N., McDaniel, P. D., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.07528 · Cited by 185
Mitigating Adversarial Effects Through Randomization
Xie, C., Wang, J., Zhang, Z., Ren, Z., & Yuille, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.01991 · Cited by 181
Foveation-based Mechanisms Alleviate Adversarial ExamplesPreprint
Luo, Y., Boix, X., Roig, G., Poggio, T., & Zhao, Q. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06292 · Cited by 161
DeepFool: a simple and accurate method to fool deep neural networksPreprint
Moosavi-Dezfooli, S.-M., Fawzi, A., & Pascal Frossard, B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.04599 · Cited by 154
Global training of document processing systems using graph transformer networks
Bottou, L., Bengio, Y., & LeCun, Y. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1997.609370 · Cited by 89
Semantic Perceptual Image Compression Using Deep Convolution Networks
Prakash, A., Moran, N., Garber, S., DiLillo, A., & Storer, J. A. (2017) · DCC · doi:10.1109/dcc.2017.56 · Cited by 88
Self-citationDetecting Adversarial Attacks on Neural Network Policies with Visual ForesightPreprint
Lin, Y.-C., Liu, M.-Y., Sun, M., & Huang, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.00814 · Cited by 60
Cited by
Improving Transferability of Adversarial Examples With Input Diversity
Xie, C., Zhang, Z., Zhou, Y., Bai, S., Wang, J., Ren, Z., & Yuille, A. L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00284 · Cited by 1,245
Proceedings of the 29th ACM International Conference on Multimedia
(2021) · doi:10.1145/3474085 · Cited by 922
On Adaptive Attacks to Adversarial Example Defenses
Tramer, F., Carlini, N., Brendel, W., & Madry, A. (2020) · arXiv · doi:10.48550/arxiv.2002.08347 · Cited by 486
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
Arnab, A., Miksik, O., & Torr, P. H. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00099 · Cited by 319
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
Liu, Z., Liu, Q., Liu, T., Xu, N., Lin, X., Wang, Y., & Wen, W. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00095 · Cited by 285
Metadata
- Authors
- Prakash, A., Moran, N., Garber, S., DiLillo, A., & Storer, J.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 8571-8580
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2785269845
- Cited by
- 310
- References
- 47
- FWCI
- 14.98
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.