Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Communication Theory of Secrecy Systems
Shannon, C. E. (1949) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1949.tb00928.x · Cited by 9,440 · cited 1×
“As Carlini & Wagner suggest [4], we conduct attacks with full access to the detection model to evaluate the adaptive adversary based on Kerckhoffs principle [36].”
MethodTowards 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
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 1×
“Comparing with other datasets such as Pascal VOC [15] and CamVid [3], these two dataset are more challenging due to the relatively high resolution and diverse scenes within each image.”
MethodDeep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
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
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Krähenbühl, P., & Koltun, V. (2012) · arXiv · doi:10.48550/arxiv.1210.5644 · Cited by 2,908
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00271 · Cited by 2,641
Self-citationEnsemble 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 · cited 1×
“For instance, adversarial training [17] and its variations [41,30] have been proposed and demonstrated to be effective in classification task, which is hard to adapt for the segmentation task.”
BackgroundRobust physical-world attacks on deep learning visual classification
Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00175 · Cited by 2,173
Self-citationAccessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
Sharif, M., Bhagavatula, S., Bauer, L., & Reiter, M. K. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978392 · Cited by 1,530
Representing and Recognizing the Visual Appearance of Materials Using Three-Dimensional Textons
Leung, T., & Malik, J. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011126920638 · Cited by 1,498 · cited 1×
“Semantic Segmentation has received long lasting attention in the computer vision community [25].”
BackgroundTransferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Papernot, N., McDaniel, P., & Goodfellow, I. (2016) · arXiv · doi:10.48550/arxiv.1605.07277 · Cited by 1,326 · cited 2×
“Transferability refers to the property of adversarial examples in classification tasks where one adversarial example generated against a local model can mislead another unseen model without any modification [33].”
BackgroundDelving 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
Self-citationSegmentation and Recognition Using Structure from Motion Point Clouds
Brostow, G. J., Shotton, J., Fauqueur, J., & Cipolla, R. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_5 · Cited by 1,050 · cited 1×
“Comparing with other datasets such as Pascal VOC [15] and CamVid [3], these two dataset are more challenging due to the relatively high resolution and diverse scenes within each image.”
MethodEfficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Lin, G., Shen, C., van den Hengel, A., & Reid, I. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.348 · Cited by 862
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2018) · arXiv · doi:10.48550/arxiv.1805.04687 · Cited by 204
Self-citation
Cited by
Adversarial Attacks and Defenses in Deep Learning
Ren, K., Zheng, T., Qin, Z., & Liu, X. (2020) · Engineering · doi:10.1016/j.eng.2019.12.012 · Cited by 678
Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
Cao, Y., Xiao, C., Cyr, B., Zhou, Y., Park, W., Rampazzi, S., Chen, Q. A., Fu, K., & Mao, Z. M. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3339815 · Cited by 471
Self-citationReview of Artificial Intelligence Adversarial Attack and Defense Technologies
Qiu, S., Liu, Q., Zhou, S., & Wu, C. (2019) · Applied Sciences · doi:10.3390/app9050909 · Cited by 411
Adversarial objects against lidar-based autonomous driving systems
Cao, Y., Xiao, C., Yang, D., Fang, J., Yang, R., Liu, M., & Li, B. (2019) · arXiv · doi:10.48550/arxiv.1907.05418 · Cited by 102
“However, recent studies show that machine learning models are vulnerable to adversarial attacks [2, 8, 18, 20, 21, 23].”
BackgroundSelf-citationUnsolved Problems in ML Safety
Hendrycks, D., Carlini, N., Schulman, J., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2109.13916 · Cited by 95
“Researchers could exploit information from these different sensors and find inconsistencies in adversarial images in order to constrain and box in adversaries [202].”
Background
Metadata
- Authors
- Xiao, C., Deng, R., Li, B., Yu, F., Liu, M., & Song, D.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2018
- Pages
- 220-237
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2949789602
- Cited by
- 86
- References
- 18
- FWCI
- 4.89
- 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.