The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
An abstract domain for certifying neural networks
Open accessAbstract
We present a novel method for scalable and precise certification of deep neural networks. The key technical insight behind our approach is a new abstract domain which combines floating point polyhedra with intervals and is equipped with abstract transformers specifically tailored to the setting of neural networks. Concretely, we introduce new transformers for affine transforms, the rectified linear unit (ReLU), sigmoid, tanh, and maxpool functions. We implemented our method in a system called DeepPoly and evaluated it extensively on a range of datasets, neural architectures (including defended networks), and specifications. Our experimental results indicate that DeepPoly is more precise than prior work while scaling to large networks. We also show how to combine DeepPoly with a form of abstraction refinement based on trace partitioning. This enables us to prove, for the first time, the robustness of the network when the input image is subjected to complex perturbations such as rotations that employ linear interpolation.
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
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
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
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198
Boosting Adversarial Attacks with Momentum
Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., & Li, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00957 · Cited by 2,956
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Katz, G., Barrett, C., Dill, D. L., Julian, K., & Kochenderfer, M. J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63387-9_5 · Cited by 1,706
Automatic discovery of linear restraints among variables of a program
Cousot, P., & Halbwachs, N. (1978) · Proceedings of the 5th ACM SIGACT-SIGPLAN symposium on Principles of programming languages - POPL '78 · doi:10.1145/512760.512770 · Cited by 1,614
DeepXplore: Automated Whitebox Testing of Deep Learning Systems
Pei, K., Cao, Y., Yang, J., & Jana, S. (2017) · Proceedings of the 26th Symposium on Operating Systems Principles · doi:10.1145/3132747.3132785 · Cited by 1,217
Artificial neural networks in medical diagnosis
Amato, F., López, A., Peña-Méndez, E. M., Vaňhara, P., Hampl, A., & Havel, J. (2013) · Journal of Applied Biomedicine · doi:10.2478/v10136-012-0031-x · Cited by 898
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., & Vechev, M. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00058 · Cited by 799
Self-citationProvable defenses against adversarial examples via the convex outer adversarial polytope
Wong, E., & Kolter, J. Z. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00851 · Cited by 634
Towards Deep Neural Network Architectures Robust to Adversarial Examples
Gu, S., & Rigazio, L. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.5068 · Cited by 622
Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
Ehlers, R. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-68167-2_19 · Cited by 550
Certified Defenses against Adversarial Examples
Raghunathan, A., Steinhardt, J., & Liang, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09344 · Cited by 520
Towards Fast Computation of Certified Robustness for ReLU NetworksPreprint
Weng, T.-W., Zhang, H., Chen, H., Song, Z., Hsieh, C., Boning, D. S., Dhillon, I. S., & Daniel, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.09699 · Cited by 493
Differentiable Abstract Interpretation for Provably Robust Neural Networks
Mirman, M., Gehr, T., & Vechev, M. (2018) · International Conference on Machine Learning · Cited by 318
Self-citationAdversarial Perturbations Against Deep Neural Networks for Malware Classification
Grosse, K., Papernot, N., Manoharan, P., Michael Backes, A., & McDaniel, P. D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04435 · Cited by 299
Measuring Neural Net Robustness with ConstraintsPreprint
Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A., & Criminisi, A. (2016) · arXiv (Cornell University) · doi:10.17863/cam.26484 · Cited by 266
Formal Security Analysis of Neural Networks using Symbolic Intervals
Wang, S., Pei, K., Whitehouse, J., Yang, J., & Jana, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10829 · Cited by 265
Adversarial Manipulation of Deep RepresentationsPreprint
Sabour, S., Cao, Y., Faghri, F., & Fleet, D. J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05122 · Cited by 238
The trace partitioning abstract domain
Rival, X., & Mauborgne, L. (2007) · ACM Transactions on Programming Languages and Systems · doi:10.1145/1275497.1275501 · Cited by 184
Exploring the space of adversarial images
Tabacof, P., & Valle, E. (2016) · 2016 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727230 · Cited by 168
A Dual Approach to Scalable Verification of Deep Networks
Krishnamurthy, Dvijotham, Stanforth, R., Gowal, S., Mann, T., & Kohli, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.06567 · Cited by 162
Relational Abstract Domains for the Detection of Floating-Point Run-Time Errors
Miné, A. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24725-8_2 · Cited by 147
The Zonotope Abstract Domain Taylor1+
Ghorbal, K., Goubault, É., & Putot, S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02658-4_47 · Cited by 116
Towards Practical Verification of Machine Learning: The Case of Computer Vision SystemsPreprint
Pei, K., Zhu, L., Cao, Y., Yang, J., Vondrick, C., & Jana, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.01785 · Cited by 110
Verifying Neural Networks with Mixed Integer ProgrammingPreprint
Tjeng, V., & Tedrake, R. (2017) · arXiv (Cornell University) · Cited by 107
Fast polyhedra abstract domain
Singh, G., Püschel, M., & Vechev, M. (2016) · ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · doi:10.1145/3009837.3009885 · Cited by 87
Self-citationGround-Truth Adversarial Examples
Carlini, N., Katz, G., Barrett, C., & Dill, D. L. (2018) · Cited by 49
A practical construction for decomposing numerical abstract domains
Singh, G., Püschel, M., & Vechev, M. (2017) · Proceedings of the ACM on Programming Languages · doi:10.1145/3158143 · Cited by 30
Self-citation
Cited by
Introduction to Neural Network Verification
Albarghouthi, A. (2021) · Foundations and Trends® in Programming Languages · doi:10.1561/2500000051 · Cited by 78
A Systematic Review of Adversarial Machine Learning Attacks, Defensive Controls and Technologies
Malik, J., Muthalagu, R., & Pawar, P. M. (2024) · IEEE Access · doi:10.1109/access.2024.3423323 · Cited by 76
Security and Privacy Issues in Deep Learning
Bae, H., Jang, J., Jung, D., Jang, H., Ha, H., Lee, H., & Yoon, S. (2018) · arXiv · doi:10.48550/arxiv.1807.11655 · Cited by 56
Efficient Exact Verification of Binarized Neural Networks
Jia, K., & Rinard, M. (2020) · arXiv · doi:10.48550/arxiv.2005.03597 · Cited by 33
Metadata
- Authors
- Singh, G., Gehr, T., Püschel, M., & Vechev, M.
- Venue
- Proceedings of the ACM on Programming Languages
- Published
- 2019-01-02
- Volume
- 3
- Issue
- POPL
- Pages
- 1-30
- ISSN
- 2475-1421 (ISSN-L)
- OpenAlex
- W2900153411
- Cited by
- 609
- References
- 31
- FWCI
- 46.66
- Type
- journal article
- Language
- en
- Open access
- diamond
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.