The Robustness of Modern Deep Learning Architectures against Single Event Upset Errors
The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Abstract
The following topics are dealt with: graph theory; parallel processing; graphics processing units; optimisation; field programmable gate arrays; learning (artificial intelligence); multiprocessing systems; data analysis; parallel architectures; microprocessor chips.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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 · cited 3×
“In the case of this paper Microsoft’s 50 layer network is tested, although they also implemented a 152 layer network.”
InfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“A. VGG16 VGG16 was introduced in 2014 by the Visual Geometry Group at Oxford [27].”
MethodImageNet 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 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“No training was needed because the models were instantiated with weights provided by the original researchers for classification against the ImageNet dataset [33].”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“Some differences are that ResNet50 uses a stride of 2 in the convolutional layers, does not use dropout during training, and utilizes batch normalization [30] between the convolutional layers.”
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381 · cited 1×
“An exciting research trend regarding the robustness of modern neural networks is the discovery of adversarial examples that can fool deep convolutional neural networks [23] [24].”
BackgroundSpeech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundIntriguing 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 · cited 1×
“An exciting research trend regarding the robustness of modern neural networks is the discovery of adversarial examples that can fool deep convolutional neural networks [23] [24].”
BackgroundAdaptive Neural Network Control of an Uncertain Robot With Full-State Constraints
He, W., Chen, Y., & Yin, Z. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2411285 · Cited by 1,273 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundFlipping bits in memory without accessing them: an experimental study of DRAM disturbance errors
Kim, Y., Daly, R., Kim, J., Fallin, C., Lee, J. H., Lee, D., Wilkerson, C., Lai, K., & Mutlu, O. (2014) · ACM SIGARCH Computer Architecture News · doi:10.1145/2678373.2665726 · Cited by 921
Flipping bits in memory without accessing them: An experimental study of DRAM disturbance errors
Kim, Y., Daly, R., Kim, J., Fallin, C., Lee, J. H., Lee, D., Wilkerson, C., Lai, K., & Mutlu, O. (2014) · 2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2014.6853210 · Cited by 465
The space radiation environment for electronics
Stassinopoulos, E. G., & Raymond, J. P. (1988) · Proceedings of the IEEE · doi:10.1109/5.90113 · Cited by 376 · cited 1×
“Beyond just malicious code, there are natural causes for DRAM memory errors such as cosmic rays [10].”
BackgroundCurrent and Future Challenges in Radiation Effects on CMOS Electronics
Dodd, P. E., Shaneyfelt, M. R., Schwank, J. R., & Felix, J. A. (2010) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2010.2042613 · Cited by 374 · cited 1×
“Satellites and spacecraft in orbit or traveling to other planets suffer a wide variety of negative effects from radiation and must be built to withstand charged particles [16] [17].”
BackgroundFlip Feng Shui: Hammering a Needle in the Software Stack
Razavi, K., Gras, B., Bosman, E., Preneel, B., Giuffrida, C., & Bos, H. (2016) · VU Research Portal · Cited by 324
Can Deep Learning Revolutionize Mobile Sensing?
Lane, N. D., & Georgiev, P. (2015) · Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications · doi:10.1145/2699343.2699349 · Cited by 282 · cited 1×
“This poses challenges for software applications that utilize cloud architectures to support mobile devices [14].”
BackgroundHwang, A. A., Stefanovici, I. A., & Schroeder, B. (2012) · Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/2150976.2150989 · Cited by 242 · cited 1×
“Although Earth’s magnetic field keeps most harmful radiation away from the surface of the earth, some particles still get through and affect large computing clusters because big data centers and servers are very large targets [11] [12] [13].”
BackgroundCan We Trust AI-Powered Real-Time Embedded Systems? (Invited Paper)
Buttazzo, G. (2022) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2022.1 · Cited by 240
Meza, J., Wu, Q., Kumar, S., & Mutlu, O. (2015) · 2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks · doi:10.1109/dsn.2015.57 · Cited by 226 · cited 1×
“Although Earth’s magnetic field keeps most harmful radiation away from the surface of the earth, some particles still get through and affect large computing clusters because big data centers and servers are very large targets [11] [12] [13].”
BackgroundSensitivity of feedforward neural networks to weight errors
Stevenson, M., Winter, R., & Widrow, B. (1990) · IEEE Transactions on Neural Networks · doi:10.1109/72.80206 · Cited by 221 · cited 1×
“Neural networks are several decades old, and there are early papers exploring the robustness of those old neural networks [18] [19] [20], but the networks of the 1990s are typically much smaller than the modern architectures explored in this paper and thus the topic deserves re-exploration.”
BackgroundPedestrian detection with convolutional neural networks
Szarvas, M., Yoshizawa, A., Yamamoto, M., & Ogata, J. (2005) · IEEE Proceedings. Intelligent Vehicles Symposium, 2005. · doi:10.1109/ivs.2005.1505106 · Cited by 205 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundBatch normalized recurrent neural networks
Laurent, C., Pereyra, G., Brakel, P., Zhang, Y., & Bengio, Y. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472159 · Cited by 201 · cited 1×
“Recurrent neural networks for example are often used for natural language processing and it is possible to use batch normalization with those networks [34].”
MethodA study of DRAM failures in the field
Sridharan, V., & Liberty, D. (2012) · 2012 International Conference for High Performance Computing, Networking, Storage and Analysis · doi:10.1109/sc.2012.13 · Cited by 186 · cited 1×
“Although Earth’s magnetic field keeps most harmful radiation away from the surface of the earth, some particles still get through and affect large computing clusters because big data centers and servers are very large targets [11] [12] [13].”
BackgroundFault tolerance in artificial neural networks
Séquin, C. H., & Clay, R. (1990) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1990.137651 · Cited by 122 · cited 1×
“Other papers explore the loss of an entire node of the neural network [21] [22] as opposed to the bit flipping model explored in this paper.”
BackgroundGamma-ray irradiation test of electric components of rescue mobile robot Quince
Nagatani, K., Kiribayashi, S., Okada, Y., Otake, K., Yoshida, K., Tadokoro, S., Nishimura, T., Yoshida, T., Koyanagi, E., Fukushima, M., et al. (2011) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2011.6106756 · Cited by 62 · cited 1×
“[15].”
Signal detection effects on deep neural networks utilizing raw IQ for modulation classification
Hauser, S. C., Headley, W. C., & Michaels, A. J. (2017) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2017.8170853 · Cited by 55 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundSelf-citationMhamdi, E. M. E., & Guerraoui, R. (2017) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2017.66 · Cited by 42 · cited 1×
“Other papers explore the loss of an entire node of the neural network [21] [22] as opposed to the bit flipping model explored in this paper.”
BackgroundThe effect of weight errors on neural networks
Arechiga, A. P., & Michaels, A. J. (2018) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc.2018.8301749 · Cited by 30 · cited 2×
“In [26] the robustness of MLPs and very small CNNs to bit flips is tested.”
BackgroundResultSelf-citationVelazco, R., Cheynet, P., Tissot, A., HAUSSY, J., Lambert, J., & Ecoffet, R. (2003) · European Conference on Radiation and Its Effects on Components and Systems · doi:10.1109/radecs.1999.858648 · Cited by 23
Velazco, R., Cheynet, P., Muller, J. D., Ecoffet, R., & Buchner, S. P. (1997) · IEEE Transactions on Nuclear Science · doi:10.1109/23.659057 · Cited by 18 · cited 1×
“Neural networks are several decades old, and there are early papers exploring the robustness of those old neural networks [18] [19] [20], but the networks of the 1990s are typically much smaller than the modern architectures explored in this paper and thus the topic deserves re-exploration.”
BackgroundEstimation of transmitter I/Q imbalance using convolutional neural networks
Wong, L. J., Headley, W. C., & Michaels, A. J. (2018) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc.2018.8301715 · Cited by 14 · cited 1×
“Neural networks’ greatest successes have been in computer vision tasks [1] [2] [3], but they have also been applied to tasks such as language processing [4], robotic control [5], and signal processing [6] [7].”
BackgroundSelf-citationMeasuring error-tolerance in SRAM architecture on hardware accelerated neural network
Kwon, S., Lee, K., Kim, Y., Kim, K., Lee, C., & Ro, W. W. (2016) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia.2016.7804818 · Cited by 12 · cited 2×
“In [25] they test the robustness of the LeNet architecture to injecting Gaussian noise into the weights of the network.”
BackgroundResultSpacecraft Environments Interactive: Space Radiation and Its Effects on Electronic System
Howard, J. W., & Hardage, D. M. (1999) · NASA STI Repository (National Aeronautics and Space Administration) · Cited by 5
Research works printed but not linked: 1
- 0, An On-device Deep Neural Network for Face Detection - Apple
Cited by
A survey on modeling and improving reliability of DNN algorithms and accelerators
Mittal, S. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.101689 · Cited by 175
A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
Ahmadilivani, M. H., Taheri, M., Raik, J., Daneshtalab, M., & Jenihhin, M. (2023) · ACM Computing Surveys · doi:10.1145/3638242 · Cited by 132
“, PyTorch (used in [59][68][70][71][72][76][78]), Keras (used in [61][62][80][81]), TensorFlow (used in [66][79]), Caffe (used in [77]), DarkNet (used in [73][140][142]).”
MethodSoft errors in DNN accelerators: A comprehensive review
Ibrahim, Y., Wang, H., Liu, J., Wei, J., Chen, L., Rech, P., Adam, K., & Guo, G. (2020) · Microelectronics Reliability · doi:10.1016/j.microrel.2020.113969 · Cited by 102
Testability and Dependability of AI Hardware: Survey, Trends, Challenges, and Perspectives
Su, F., Liu, C., & Stratigopoulos, H. (2023) · IEEE Design and Test · doi:10.1109/mdat.2023.3241116 · Cited by 97
“The interested reader is referred to [70], [71], [72], [73], [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], and [85] for more software-based fault injection experiments studying the fault impact for different neural network models, data type representations, layer types, network sizes, pruned networ…”
BackgroundA Survey of Bit-Flip Attacks on Deep Neural Network and Corresponding Defense Methods
Qian, C., Zhang, M., Nie, Y., Lu, S., & Cao, H. (2023) · Electronics · doi:10.3390/electronics12040853 · Cited by 42
Metadata
- Authors
- Arechiga, A. P., & Michaels, A. J.
- ORCID
- Michaels, Alan J.
- Venue
- 2018 IEEE High Performance extreme Computing Conference (HPEC)
- Publisher
- IEEE
- Published
- 2018-09
- Pages
- 1-6
- OpenAlex
- W2902083778
- Cited by
- 47
- References
- 37
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 10 · 2023: 7 · 2022: 9 · 2021: 5 · 2020: 7 · 2019: 2
- FWCI
- 5.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE High Performance Extreme Computing Conference (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Radiation Effects in Electronics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- single event upset, deep learning robustness, hardware errors, fault tolerance, neural network reliability
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.