The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Adversarial frontier stitching for remote neural network watermarking
Open accessAbstract
The state-of-the-art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, Nagai et al. (Int J Multimed Inf Retr 7(1):3–16, 2018), Uchida et al. (Embedding watermarks into deep neural networks, ICMR, 2017) proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress toward model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely. Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machine learning model) that is operated remotely, and available through a service API. To this end, we propose to mark the model’s action itself, tweaking slightly its decision frontiers so that a set of specific queries convey the desired information. In the present paper, we formally introduce the problem and propose a novel zero-bit watermarking algorithm that makes use of adversarial model examples. While limiting the loss of performance of the protected model, this algorithm allows subsequent extraction of the watermark using only few queries. We experimented the approach on three neural networks designed for image classification, in the context of MNIST digit recognition task.
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
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
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
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
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
Adversarial Examples: Attacks and Defenses for Deep Learning
Yuan, X., He, P., Zhu, Q., & Li, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2886017 · Cited by 1,733
Multimedia watermarking techniques
Hartung, F., & Kutter, M. (1999) · Proceedings of the IEEE · doi:10.1109/5.771066 · Cited by 1,363
Trojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
van Schyndel, R. G., Tirkel, A. Z., & Osborne, C. F. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413536 · Cited by 1,139
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
Carlini, N., & Wagner, D. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00009 · Cited by 1,035
Embedding Watermarks into Deep Neural Networks
Uchida, Y., Nagai, Y., Sakazawa, S., & Satoh, S. (2017) · Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval · doi:10.1145/3078971.3078974 · Cited by 676
Protecting Intellectual Property of Deep Neural Networks with Watermarking
Zhang, J., Gu, Z., Jang, J., Wu, H., Stoecklin, M. P., Huang, H., & Molloy, I. (2018) · Proceedings of the 2018 on Asia Conference on Computer and Communications Security · doi:10.1145/3196494.3196550 · Cited by 540
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
Le, Q. V., Jaitly, N., & Hinton, G. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.00941 · Cited by 513
Stealing Hyperparameters in Machine Learning
Wang, B., & Gong, N. Z. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00038 · Cited by 470
On the (Statistical) Detection of Adversarial Examples
Grosse, K., Manoharan, P., Papernot, N., Michael Backes, A., & McDaniel, P. D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.06280 · Cited by 330
Are Adversarial Examples Inevitable?
Shafahi, A., Huang, W., Studer, C., Feizi, S., & Goldstein, T. (2018) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000460350 · Cited by 292
Towards Reverse-Engineering Black-Box Neural Networks
Oh, S. J., Schiele, B., & Fritz, M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-28954-6_7 · Cited by 291
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 255
DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning ModelsPreprint
Rouhani, B. D., Chen, H., & Koushanfar, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.00750 · Cited by 178
cleverhans v0.1: an adversarial machine learning library.Preprint
Goodfellow, I., Papernot, N., & McDaniel, P. D. (2016) · arXiv (Cornell University) · Cited by 177
Stealing Neural Networks via Timing Side ChannelsPreprint
Duddu, V., Samanta, D., Rao, D. V., & Bălaş, V. E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11720 · Cited by 172
Watermarking deep neural networks for embedded systems
Guo, J., & Potkonjak, M. (2018) · Proceedings of the International Conference on Computer-Aided Design · doi:10.1145/3240765.3240862 · Cited by 161
Digital watermarking for deep neural networks
Nagai, Y., Uchida, Y., Sakazawa, S., & Satoh, S. (2018) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-018-0147-1 · Cited by 152
Stealthy Adversarial Perturbations Against Real-Time Video Classification Systems
Li, S., Neupane, A., Paul, S., Song, C., Krishnamurthy, S. V., Chowdhury, A. K. R., & Swami, A. (2019) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23202 · Cited by 126
Data driven exploratory attacks on black box classifiers in adversarial domains
Sethi, T. S., & Kantardzic, M. M. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.007 · Cited by 56
Are Accuracy and Robustness Correlated
Rozsa, A., Günther, M., & Boult, T. E. (2016) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2016.0045 · Cited by 54
Zhao, X., Liu, Q., Zheng, H.-T., & Zhao, B. Y. (2015) · Conference on Online Social Networks · doi:10.1145/2817946.2817956 · Cited by 23
An Empirical Evaluation of Adversarial Robustness under Transfer LearningPreprint
Davchev, T., Korres, T., Fotiadis, S., Antonopoulos, N., & Ramamoorthy, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.02675 · Cited by 13
Some Insights into the Geometry and Training of Neural Networks
van den Berg, E. (2018) · The MIT Press eBooks · doi:10.7551/mitpress/10012.003.0001 · Cited by 5
TamperNN: Efficient Tampering Detection of Deployed Neural Nets
Merrer, E. L., & Trédan, G. (2019) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre.2019.00049 · Cited by 5
Self-citation
Cited by
Protecting Intellectual Property of Deep Neural Networks with Watermarking
Zhang, J., Gu, Z., Jang, J., Wu, H., Stoecklin, M. P., Huang, H., & Molloy, I. (2018) · Proceedings of the 2018 on Asia Conference on Computer and Communications Security · doi:10.1145/3196494.3196550 · Cited by 540
Privacy and Security Issues in Deep Learning: A Survey
Liu, X., Xie, L., Wang, Y., Zou, J., Xiong, J., Ying, Z., & Vasilakos, A. V. (2021) · IEEE Access · doi:10.1109/access.2020.3045078 · Cited by 282
A comprehensive survey on robust image watermarking
Wan, W., Wang, J., Zhang, Y., Li, J., Yu, H., & Sun, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.083 · Cited by 264
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01418 · Cited by 195
A survey of Deep Neural Network watermarking techniques
Li, Y., Wang, H., & Barni, M. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.051 · Cited by 177
Metadata
- Authors
- Le Merrer, E., Pérez, P., & Trédan, G.
- Venue
- Neural Computing and Applications
- Published
- 2019-08-17
- Volume
- 32
- Issue
- 13
- Pages
- 9233-9244
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W2768064608
- Cited by
- 341
- References
- 31
- FWCI
- 17.15
- Type
- journal article
- 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.