Seeing isn't Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Recently Adversarial Examples (AEs) that deceive deep learning models have been a topic of intense research interest. Compared with the AEs in the digital space, the physical adversarial attack is considered as a more severe threat to the applications like face recognition in authentication, objection detection in autonomous driving cars, etc. In particular, deceiving the object detectors practically, is more challenging since the relative position between the object and the detector may keep changing. Existing works attacking object detectors are still very limited in various scenarios, e.g., varying distance and angles, etc. In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors. Particularly, for Hiding Attack (HA), we proposed thefeature-interference reinforcement (FIR) method and theenhanced realistic constraints generation (ERG) to enhance robustness, and for Appearing Attack (AA), we proposed thenested-AE, which combines two AEs together to attack object detectors in both long and short distance. We also designed diverse styles of AEs to make AA more surreptitious. Evaluation results show that our AEs can attack the state-of-the-art real-time object detectors (i.e., YOLO V3 and faster-RCNN) at the success rate up to 92.4% with varying distance from 1m to 25m and angles from -60º to 60º. Our AEs are also demonstrated to be highly transferable, capable of attacking another three state-of-the-art black-box models with high success rate.
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 3×
“Faster RCNN, a two-stage detection framework, includes a preprocessing step for region proposals and a category-specific classification step to determine the category labels of the proposals [34].”
BackgroundMethodYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 2×
“…categories: two-stage strategy detectors such as Faster RCNN [34], RCNN [17], SPPNet [21], Fast RCNN [16], RFCN [11], Mask RCNN [20], Light Head RCNN [24], etc., and one-stage detectors including DetectorNet [46], OverFeat [36], YOLO [31], YOLO V2 and YOLO 9000 [32], SSD [27], YOLO V3 [33], etc.”
BackgroundMethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 2×
“…categories: two-stage strategy detectors such as Faster RCNN [34], RCNN [17], SPPNet [21], Fast RCNN [16], RFCN [11], Mask RCNN [20], Light Head RCNN [24], etc., and one-stage detectors including DetectorNet [46], OverFeat [36], YOLO [31], YOLO V2 and YOLO 9000 [32], SSD [27], YOLO V3 [33], etc.”
MethodYOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
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 · cited 1×
“There have been a lot of prior works [29] [9] [22] [45] on investigating the vulnerability of deep neural networks against adversarial examples.”
BackgroundAdversarial 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
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
R-FCN: Object Detection via Region-based Fully Convolutional Networks
Dai, J., Li, Y., He, K., & Sun, J. Z. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.06409 · Cited by 3,149
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 · cited 1×
“(2) Improving the models such as the adversarial training [40], defense distillation [30] and gradients obfuscation [6].”
BackgroundDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965 · cited 1×
“Faster RCNN is proposed to improve the RCNN, which is quite computationally expensive in spite of high object detection accuracy [26].”
MethodDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 2×
“…categories: two-stage strategy detectors such as Faster RCNN [34], RCNN [17], SPPNet [21], Fast RCNN [16], RFCN [11], Mask RCNN [20], Light Head RCNN [24], etc., and one-stage detectors including DetectorNet [46], OverFeat [36], YOLO [31], YOLO V2 and YOLO 9000 [32], SSD [27], YOLO V3 [33], etc.”
BackgroundMethodEnsemble 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×
“(2) Improving the models such as the adversarial training [40], defense distillation [30] and gradients obfuscation [6].”
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
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Athalye, A., Carlini, N., & Wagner, D. (2018) · arXiv · doi:10.48550/arxiv.1802.00420 · Cited by 2,172 · cited 1×
“(2) Improving the models such as the adversarial training [40], defense distillation [30] and gradients obfuscation [6].”
BackgroundAccessorize 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 · cited 1×
“For example, in the work of the physical attack against face detection presented in [37], the authors printed sun glasses that are capable of deceiving the state-of-the-art face recognition system.”
BackgroundFeature denoising for improving adversarial robustness
Xie, C., Wu, Y., Maaten, L. V. D., Yuille, A. L., & He, K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00059 · Cited by 940 · cited 1×
“The defense mechanisms we consider can be grouped into three categories: (1) Modifying the inputs to disturb or even remove the adversarial perturbations, e.g., JPEG compression [12], randomization [41], median-filter [43], image re-scaling [19], etc.”
Background13th USENIX Workshop on Offensive Technologies, WOOT 2019
Gantman, A., & Maurice, C. (2019) · HAL · Cited by 940
Adversarial Examples for Semantic Segmentation and Object Detection
Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., & Yuille, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.153 · Cited by 924 · cited 1×
“[42] extended adversarial examples to semantic segmentation and object detection in the digital space.”
BackgroundDefense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., & Zhu, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00191 · Cited by 902
Brown, T. B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017) · arXiv · doi:10.48550/arxiv.1712.09665 · Cited by 509 · cited 4×
“Tom et al. presented a method to create adversarial image patches that could be printed and attached to the target to fool image classifiers [8].”
BackgroundMethodInfluentialLight-Head R-CNN: In Defense of Two-Stage Object Detector
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1711.07264 · Cited by 292 · cited 2×
“Modern object detectors based on deep learning methods can be classified into two categories: two-stage strategy detectors such as Faster RCNN [34], RCNN [17], SPPNet [21], Fast RCNN [16], RFCN [11], Mask RCNN [20], Light Head RCNN [24], etc., and one-stage detectors including DetectorNet [46], OverFeat [36], YOLO [31…”
MethodAdversarial Examples for Generative Models
Kos, J., Fischer, I., & Song, D. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00014 · Cited by 230
Metadata
- Authors
- Zhao, Y., Zhu, H., Liang, R., Shen, Q., Zhang, S., & Chen, K.
- Venue
- Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2019-11-06
- Pages
- 1989-2004
- OpenAlex
- W2984260944
- Cited by
- 164
- References
- 28
- FWCI
- 6.41
- Type
- conference paper
- Language
- en
- Open access
- closed
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.