Evaluating Fault Resiliency of Compressed Deep Neural Networks
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Model compression is considered to be an effective way to reduce the implementation cost of deep neural networks (DNNs) while maintaining the inference accuracy. Many recent studies have developed efficient model compression algorithms and implementations in accelerators on various devices. Protecting integrity of DNN inference against fault attacks is important for diverse deep learning enabled applications. However, there has been little research investigating the fault resilience of DNNs and the impact of model compression on fault tolerance. In this work, we consider faults on different data types and develop a simulation framework for understanding the fault resiliency of compressed DNN models as compared to uncompressed models. We perform our experiments on two common DNNs, LeNet-5 and VGG16, and evaluate their fault resiliency with different types of compression. The results show that binary quantization can effectively increase the fault resilience of DNN models by 10000x for both LeNet5 and VGG16. Finally, we propose software and hardware mitigation techniques to increase the fault resiliency of DNN models.
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
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 both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481 · cited 1×
“The accuracy of a DNN inference engine after model compression is often higher than that of a smaller neural network with no compression [13], [14].”
BackgroundFixed Point Quantization of Deep Convolutional Networks
Lin, D. D., Talathi, S. S., & Annapureddy, V. S. (2015) · arXiv · doi:10.48550/arxiv.1511.06393 · Cited by 684 · cited 1×
“Many research work [15]–[17] focus on the quantization of weights to binary values, ternary values, or powers of 2 to facilitate hardware implementations, with acceptable accuracy loss.”
BackgroundAndo, K., Ueyoshi, K., Orimo, K., Yonekawa, H., Sato, S., Nakahara, H., Takamaeda-Yamazaki, S., Ikebe, M., Asai, T., Kuroda, T., et al. (2018) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2017.2778702 · Cited by 160
Research works printed but not linked: 20
- lecun, 0, MNIST Handwritten Digit Database
- krizhevsk, 0, Cifar-10 (canadian institute for advanced research)
- wen, 0, Learning structured sparsity in deep neural networks, Proc Int Conf on Neural Information Processing Systems, 2082
- rastegari, 2016, XNOR-Net: ImageNet classification using binary convolutional neural networks, Lecture Notes in Computer Science, 525542
- leng, 2017, Extremely low bit neural network Squeeze the last bit out with admm
- 10.1109/CVPR.2016.521 · DOI · Paper page
- lowery, 2013, Relative error due to a single bit-flip in floating-point arithmetic
- 10.1145/3007787.3001139 · DOI · Paper page
- fowers, 0, A configurable cloud-scale DNN processor for realtime AI, Proc Int Symp on Computer Architecture, 1
- 10.1145/3195970.3195997 · DOI · Paper page
- simonyan, 0, Very deep convolutional networks for large-scale image recognition, Int Conf on Learning Representations
- 10.1145/3289602.3293915 · DOI
- ye, 2019, Progressive DNN compression A key to achieve ultrahigh weight pruning and quantization rates using ADMM
- 10.1109/ICDCS.2018.00139 · DOI · Paper page
- 10.1007/978-3-319-16763-3_15 · doi:10.1007/978-3-319-16763-3_15
- tang, 0, CLKSCREW: Exposing the perils of security-oblivious energy management, Usenix Security Symp, 1057
- 10.1109/DATE.2007.364528 · doi:10.1109/date.2007.364528
- 10.1109/TNS.2018.2884460 · DOI · Paper page
- 10.1145/3126908.3126964 · DOI · Paper page
- 10.1109/EMPDP.2019.8671543 · DOI
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
TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
Chen, Z., Narayanan, N., Fang, B., Li, G., Pattabiraman, K., & DeBardeleben, N. (2020) · 2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre5003.2020.00047 · Cited by 93
Soft Error Reliability Analysis of Vision Transformers
Xue, X., Liu, C., Wang, Y., Yang, B., Luo, T., Zhang, L., Li, H., & Li, X. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3317138 · Cited by 35
“Sabbagh et al. [25] mainly evaluated the impact of model compression especially pruning and quantization on the resilience of CNNs. Xu et al. [14], [26] leveraged FPGA-based fault injection to evaluate the influence of persistent faults on neural network models and particularly investigated the…”
BackgroundSelf-citationFine-Grained Fault Sensitivity Analysis of Vision Transformers Under Soft Errors
He, J., Liu, Y., Xu, C., Liao, X., & Yang, Y. (2025) · Electronics · doi:10.3390/electronics14122418 · Cited by 4
Metadata
- Authors
- Sabbagh, M., Gongye, C., Fei, Y., & Wang, Y.
- Venue
- 2019 IEEE International Conference on Embedded Software and Systems (ICESS)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 1-7
- OpenAlex
- W2964866569
- Cited by
- 42
- References
- 5
- FWCI
- 2.00
- Type
- conference paper
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluating Fault Resiliency of Compressed Deep Neural Networks. https://app.cochat.ai/papers/10.1109/icess.2019.8782505
- The paper
- Sabbagh, M., Gongye, C., Fei, Y., & Wang, Y. (2019). Evaluating Fault Resiliency of Compressed Deep Neural Networks. 2019 IEEE International Conference on Embedded Software and Systems (ICESS). https://doi.org/10.1109/icess.2019.8782505
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.