The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
DeepGauge: multi-granularity testing criteria for deep learning systems
Open accessAbstract
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.
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
Self-citationGradient-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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
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
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
Multi-column deep neural networks for image classification
Ciresan, D., Meier, U., & Schmidhuber, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248110 · Cited by 3,720
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
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×
“For more extensive discussion on current state-of-the-art defense techniques, we refer readers to [4].”
BackgroundAn Analysis and Survey of the Development of Mutation Testing
Jia, Y., & Harman, M. (2011) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2010.62 · Cited by 1,745
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
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
DeepTest: automated testing of deep-neural-network-driven autonomous cars
Tian, Y., Pei, K., Jana, S., & Ray, B. (2018) · Proceedings of the 40th International Conference on Software Engineering · doi:10.1145/3180155.3180220 · Cited by 1,217
Decision-based adversarial attacks: Reliable attacks against black-box machine learning models
Brendel, W., Rauber, J., & Bethge, M. (2017) · arXiv · doi:10.48550/arxiv.1712.04248 · Cited by 1,018 · cited 1×
“Ever since the inception of adversarial attacks on the DL systems, more and more research has been dedicated to building up strong attackers [6, 25, 55, 60].”
BackgroundAdversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
Carlini, N., & Wagner, D. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140444 · Cited by 966
Fraser, G., & Arcuri, A. (2013) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2012.14 · Cited by 586 · cited 1×
“, statement coverage, branch coverage) towards the exploration of diverse software states for defect detection has become the de facto standard in traditional software testing [5, 16, 17, 33], the study to design suitable testing criteria for DL is desperately demanding.”
BackgroundPixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Song, Y., Kim, T., Nowozin, S., Ermon, S., & Kushman, N. (2017) · arXiv · doi:10.48550/arxiv.1710.10766 · Cited by 562
Generating Natural Adversarial Examples
Zhao, Z., Dua, D., & Singh, S. (2017) · arXiv · doi:10.48550/arxiv.1710.11342 · Cited by 508 · cited 2×
“A plethora of research has shown that deep learning systems can be fooled by applying carefully crafted adversarial perturbation added to the original input [6–9, 20, 48, 55, 60], many of which are based on gradient or optimization techniques.”
BackgroundA survey on model-based testing approaches: a systematic review
Dias Neto, A. C., Subramanyan, R., Vieira, M., & Travassos, G. H. (2007) · Proceedings of the 1st ACM international workshop on Empirical assessment of software engineering languages and technologies: held in conjunction with the 22nd IEEE/ACM International Conference on Automated Software Engineering (ASE) 2007 · doi:10.1145/1353673.1353681 · Cited by 306
An Abstraction-Refinement Approach to Verification of Artificial Neural Networks
Pulina, L., & Tacchella, A. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-14295-6_24 · Cited by 261
Su, T., Wu, K., Miao, W., Pu, G., He, J., Chen, Y., & Su, Z. (2017) · ACM Computing Surveys · doi:10.1145/3020266 · Cited by 109
Self-citationGRT: Program-Analysis-Guided Random Testing (T)
Ma, L., Artho, C. V., Zhang, C., Satō, H., Gmeiner, J., & Ramler, R. (2015) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2015.49 · Cited by 92
Self-citation
Cited by
Machine Learning Testing: Survey, Landscapes and Horizons
Zhang, J. M., Harman, M., Ma, L., & Liu, Y. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2962027 · Cited by 897
Self-citationTrustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
“Such coverage criteria are effective for certifying the robustness of a DNN against adversarial attacks [226].”
BackgroundMethodInfluentialSelf-citationDeepHunter: a coverage-guided fuzz testing framework for deep neural networks
Xie, X., Ma, L., Juefei-Xu, F., Xue, M., Chen, H., Liu, Y., Zhao, J., Li, B., Yin, J., & See, S. (2019) · Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis · doi:10.1145/3293882.3330579 · Cited by 426
Self-citationDeepMutation: 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
Self-citationDeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.07634 · Cited by 280
Self-citation
Metadata
- Authors
- Ma, L., Juefei-Xu, F., Zhang, F., Sun, J., Xue, M., Li, B., Chen, C., Su, T., Li, L., Liu, Y., Zhao, J., & Wang, Y.
- Venue
- Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering
- Publisher
- ACM
- Published
- 2018-09-03
- Pages
- 120-131
- OpenAlex
- W2804337238
- Cited by
- 588
- References
- 22
- FWCI
- 33.13
- 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.