The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Open accessAbstract
We present AI2, the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI2can automatically prove safety properties (e.g., robustness) of realistic neural networks (e.g., convolutional neural networks). The key insight behind AI2is to phrase reasoning about safety and robustness of neural networks in terms of classic abstract interpretation, enabling us to leverage decades of advances in that area. Concretely, we introduce abstract transformers that capture the behavior of fully connected and convolutional neural network layers with rectified linear unit activations (ReLU), as well as max pooling layers. This allows us to handle real-world neural networks, which are often built out of those types of layers. We present a complete implementation of AI2together with an extensive evaluation on 20 neural networks. Our results demonstrate that: (i) AI2is precise enough to prove useful specifications (e.g., robustness), (ii) AI2can be used to certify the effectiveness of state-of-the-art defenses for neural networks, (iii) AI2is significantly faster than existing analyzers based on symbolic analysis, which often take hours to verify simple fully connected networks, and (iv) AI2can handle deep convolutional networks, which are beyond the reach of existing methods.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
Hubel, D. H., & Wiesel, T. N. (1962) · The Journal of Physiology · doi:10.1113/jphysiol.1962.sp006837 · Cited by 13,680
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
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
Cousot, P., & Cousot, R. (1977) · Proceedings of the 4th ACM SIGACT-SIGPLAN symposium on Principles of programming languages - POPL '77 · doi:10.1145/512950.512973 · Cited by 6,279
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
Cited by
Certified Robustness to Adversarial Examples with Differential Privacy
Lecuyer, M., Atlidakis, V., Geambasu, R., Hsu, D., & Jana, S. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00044 · Cited by 750
An abstract domain for certifying neural networks
Singh, G., Gehr, T., Püschel, M., & Vechev, M. (2019) · Proceedings of the ACM on Programming Languages · doi:10.1145/3290354 · Cited by 609
Self-citationHuang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M., & Yi, X. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100270 · Cited by 532
The Marabou Framework for Verification and Analysis of Deep Neural Networks
Katz, G., Huang, D. A., Ibeling, D., Julian, K., Lazarus, C., Lim, R., Shah, P., Thakoor, S., Wu, H., Zeljić, A., et al. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-25540-4_26 · Cited by 517
“Several recent papers have proposed verification schemes that rely on DNNlevel reasoning [5,23].”
BackgroundMethodThinking responsibly about responsible AI and ‘the dark side’ of AI
Mikalef, P., Conboy, K., Lundström, J. E., & Popovič, A. (2022) · European Journal of Information Systems · doi:10.1080/0960085x.2022.2026621 · Cited by 435
DeepMutation: Mutation Testing of Deep Learning Systems
Ma, L., Zhang, F., Sun, J., Xue, M., Li, B., Juefei-Xu, F., Xie, C., Li, L., Liu, Y., Zhao, J., et al. (2018) · 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre.2018.00021 · Cited by 366
Concolic testing for deep neural networks
Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M., & Kroening, D. (2018) · Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering · doi:10.1145/3238147.3238172 · Cited by 332
Efficient Neural Network Robustness Certification with General Activation Functions
Zhang, H., Weng, T.-W., Chen, P., Hsieh, C., & Daniel, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00866 · Cited by 316
Camilleri, M. A. (2024) · Expert Systems · doi:10.1111/exsy.13406 · Cited by 331
LEMNA: Explaining Deep Learning based Security Applications
Guo, W., Mu, D., Xu, J., Su, P., Wang, G., & Xing, X. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243792 · Cited by 287
On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
Gowal, S., Dvijotham, K., Stanforth, R., Bunel, R., Qin, C., Uesato, J., Arandjelović, R., Mann, T., & Kohli, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12715 · Cited by 261
The Fallacy of AI Functionality
Raji, I. D., Kumar, I. E., Horowitz, A., & Selbst, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533158 · Cited by 251
Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
Ashmore, R., Calinescu, R., & Paterson, C. (2022) · ACM Computing Surveys · doi:10.1145/3453444 · Cited by 256
Toward verified artificial intelligence
Seshia, S. A., Sadigh, D., & Sastry, S. S. (2022) · Communications of the ACM · doi:10.1145/3503914 · Cited by 215
Fu, Y., Li, C., Yu, F. R., Luan, T. H., & Zhang, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3083927 · Cited by 169
DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
Han, D., Wang, Z., Chen, W., Zhong, Y., Wang, S., Zhang, H., Yang, J., Shi, X., & Yin, X. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484589 · Cited by 121
A Review on Human–Machine Trust Evaluation: Human-Centric and Machine-Centric Perspectives
Gebru, B., Zeleke, L., Blankson, D., Nabil, M., Nateghi, S., Homaifar, A., & Tunstel, E. (2022) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2022.3144956 · Cited by 101
Artificial intelligence in safety-critical systems: a systematic review
Wang, Y., & Chung, S. H. (2022) · Industrial Management & Data Systems · doi:10.1108/imds-07-2021-0419 · Cited by 96
Introduction to Neural Network Verification
Albarghouthi, A. (2021) · Foundations and Trends® in Programming Languages · doi:10.1561/2500000051 · Cited by 78
Probabilistic verification of fairness properties via concentration
Bastani, O., Zhang, X., & Solar-Lezama, A. (2019) · Proceedings of the ACM on Programming Languages · doi:10.1145/3360544 · Cited by 57
Abduction-Based Explanations for Machine Learning Models
Ignatiev, A., Narodytska, N., & Marques-Silva, J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011511 · Cited by 40
Efficient Exact Verification of Binarized Neural Networks
Jia, K., & Rinard, M. (2020) · arXiv · doi:10.48550/arxiv.2005.03597 · Cited by 33
Directions of Technical Innovation for Regulatable AI Systems
Shen, X., Brown, H., Tao, J., Strobel, M., Tong, Y., Narayan, A., Soh, H., & Doshi-Velez, F. (2024) · Communications of the ACM · doi:10.1145/3653670 · Cited by 3
Metadata
- Authors
- Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., & Vechev, M.
- Venue
- 2018 IEEE Symposium on Security and Privacy (SP)
- Publisher
- IEEE
- Published
- 2018-05
- Pages
- 3-18
- ISSN
- 1081-6011 (ISSN-L)
- OpenAlex
- W2794609696
- Cited by
- 799
- References
- 40
- FWCI
- 108.77
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.