{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:20:23Z","timestamp":1766067623231},"reference-count":25,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.1587\/transfun.2022vlp0004","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T22:13:23Z","timestamp":1667945603000},"page":"523-531","source":"Crossref","is-referenced-by-count":2,"title":["Vulnerability Estimation of DNN Model Parameters with Few Fault Injections"],"prefix":"10.1587","volume":"E106.A","author":[{"given":"Yangchao","family":"ZHANG","sequence":"first","affiliation":[{"name":"Department of Information Systems Engineering, Graduate School of Information Science and Technology, Osaka University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"ITSUJI","sequence":"additional","affiliation":[{"name":"Electronic Systems Research Dept., Production Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research & Development Group, Hitachi, Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takumi","family":"UEZONO","sequence":"additional","affiliation":[{"name":"Electronic Systems Research Dept., Production Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research & Development Group, Hitachi, Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadanobu","family":"TOBA","sequence":"additional","affiliation":[{"name":"Electronic Systems Research Dept., Production Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research & Development Group, Hitachi, Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masanori","family":"HASHIMOTO","sequence":"additional","affiliation":[{"name":"Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] D.A.G. Gon\u00e7alves de Oliveira, L.L. Pilla, T. Santini, and P. Rech, \u201cEvaluation and mitigation of radiation-induced soft errors in graphics processing units,\u201d IEEE Trans. Comput., vol.65, no.3, pp.791-804, 2016. 10.1109\/tc.2015.2444855","DOI":"10.1109\/TC.2015.2444855"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] F.F. dos Santos, P.F. Pimenta, C. Lunardi, L. Draghetti, L. Carro, D. Kaeli, and P. Rech, \u201cAnalyzing and increasing the reliability of convolutional neural networks on GPUs,\u201d IEEE Trans. Rel., vol.68, no.2, pp.663-677, 2019. 10.1109\/tr.2018.2878387","DOI":"10.1109\/TR.2018.2878387"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] A. Lotfi, S. Hukerikar, K. Balasubramanian, P. Racunas, N. Saxena, R. Bramley, and Y. Huang, \u201cResiliency of automotive object detection networks on GPU architectures,\u201d 2019 IEEE International Test Conference (ITC), pp.1-9, 2019. 10.1109\/itc44170.2019.9000150","DOI":"10.1109\/ITC44170.2019.9000150"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] C. Lunardi, F. Previlon, D. Kaeli, and P. Rech, \u201cOn the efficacy of ECC and the benefits of FinFET transistor layout for GPU reliability,\u201d IEEE Trans. Nucl. Sci., vol.65, no.8, pp.1843-1850, 2018. 10.1109\/tns.2018.2823786","DOI":"10.1109\/TNS.2018.2823786"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] P.M. Basso, F.F. dos Santos, and P. Rech, \u201cImpact of tensor cores and mixed precision on the reliability of matrix multiplication in GPUs,\u201d IEEE Trans. Nucl. Sci., vol.67, no.7, pp.1560-1565, 2020. 10.1109\/tns.2020.2977583","DOI":"10.1109\/TNS.2020.2977583"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] P.E. Dodd and L.W. Massengill, \u201cBasic mechanisms and modeling of single-event upset in digital microelectronics,\u201d IEEE Trans. Nucl. Sci., vol.50, no.3, pp.583-602, 2003. 10.1109\/tns.2003.813129","DOI":"10.1109\/TNS.2003.813129"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Z. Yan, Y. Shi, W. Liao, M. Hashimoto, X. Zhou, and C. Zhuo, \u201cWhen single event upset meets deep neural networks: Observations, explorations, and remedies,\u201d 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), IEEE, pp.163-168, 2020. 10.1109\/asp-dac47756.2020.9045134","DOI":"10.1109\/ASP-DAC47756.2020.9045134"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] Y. Kim, R. Daly, J. Kim, C. Fallin, J.H. Lee, D. Lee, C. Wilkerson, K. Lai, and O. Mutlu, \u201cFlipping bits in memory without accessing them: An experimental study of DRAM disturbance errors,\u201d ACM SIGARCH Computer Architecture News, vol.42, no.3, pp.361-372, 2014. 10.1145\/2678373.2665726","DOI":"10.1145\/2678373.2665726"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] B. Nie, J. Xue, S. Gupta, C. Engelmann, E. Smirni, and D. Tiwari, \u201cCharacterizing temperature, power, and soft-error behaviors in data center systems: Insights, challenges, and opportunities,\u201d 2017 IEEE 25th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), pp.22-31, 2017. 10.1109\/mascots.2017.12","DOI":"10.1109\/MASCOTS.2017.12"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] G. Li, S.K.S. Hari, M. Sullivan, T. Tsai, K. Pattabiraman, J. Emer, and S.W. Keckler, \u201cUnderstanding error propagation in deep learning neural network (DNN) accelerators and applications,\u201d Proc. International Conference for High Performance Computing, Networking, Storage and Analysis, 2017. 10.1145\/3126908.3126964","DOI":"10.1145\/3126908.3126964"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] A.S. Rakin, Z. He, and D. Fan, \u201cBit-flip attack: Crushing neural network with progressive bit search,\u201d Proc. IEEE\/CVF International Conference on Computer Vision, pp.1211-1220, 2019. 10.1109\/iccv.2019.00130","DOI":"10.1109\/ICCV.2019.00130"},{"key":"12","unstructured":"[12] I.J. Goodfellow, J. Shlens, and C. Szegedy, \u201cExplaining and harnessing adversarial examples,\u201d arXiv preprint arXiv:1412.6572, 2014."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] W. Choi, D. Shin, J. Park, and S. Ghosh, \u201cSensitivity based error resilient techniques for energy efficient deep neural network accelerators,\u201d 2019 56th ACM\/IEEE Design Automation Conference (DAC), pp.1-6, 2019. 10.1145\/3316781.3317908","DOI":"10.1145\/3316781.3317908"},{"key":"14","unstructured":"[14] A. Mahmoud, S.K.S. Hari, C.W. Fletcher, S.V. Adve, C. Sakr, N. Shanbhag, P. Molchanov, M.B. Sullivan, T. Tsai, and S.W. Keckler, \u201cHarDNN: Feature map vulnerability evaluation in CNNs,\u201d arXiv preprint arXiv:2002.09786, 2020."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. Zhang, H. Itsuji, T. Uezono, T. Toba, and M. Hashimoto, \u201cEstimating vulnerability of all model parameters in DNN with a small number of fault injections,\u201d Design, Automation and Test in Europe Conference (DATE), 2022. 10.23919\/date54114.2022.9774569","DOI":"10.23919\/DATE54114.2022.9774569"},{"key":"17","unstructured":"[17] Z. Chen, G. Li, K. Pattabiraman, and N. DeBardeleben, \u201cBinFI: An efficient fault injector for safety-critical machine learning systems,\u201d Proc. International Conference for High Performance Computing, Networking, Storage and Analysis, pp.1-23, 2019. 10.1145\/3295500.3356177"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] F. Benevenuti, F. Libano, V. Pouget, F.L. Kastensmidt, and P. Rech, \u201cComparative analysis of inference errors in a neural network implemented in SRAM-based FPGA induced by neutron irradiation and fault injection methods,\u201d 2018 31st Symposium on Integrated Circuits and Systems Design (SBCCI), pp.1-6, 2018. 10.1109\/sbcci.2018.8533235","DOI":"10.1109\/SBCCI.2018.8533235"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] A. Barenghi, L. Breveglieri, I. Koren, and D. Naccache, \u201cFault injection attacks on cryptographic devices: Theory, practice, and countermeasures,\u201d Proc. IEEE, vol.100, no.11, pp.3056-3076, 2012. 10.1109\/jproc.2012.2188769","DOI":"10.1109\/JPROC.2012.2188769"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] J. Breier, X. Hou, D. Jap, L. Ma, S. Bhasin, and Y. Liu, \u201cPractical fault attack on deep neural networks,\u201d Proc. 2018 ACM SIGSAC Conference on Computer and Communications Security, pp.2204-2206, 2018. 10.1145\/3243734.3278519","DOI":"10.1145\/3243734.3278519"},{"key":"21","unstructured":"[21] H. Li, A. Kadav, I. Durdanovic, H. Samet, and H.P. Graf, \u201cPruning filters for efficient ConvNets,\u201d arXiv preprint arXiv:1608.08710, 2016."},{"key":"22","unstructured":"[22] J. Redmon and A. Farhadi, \u201cYOLOv3: An incremental improvement,\u201d arXiv preprint arXiv:1804.02767, 2018."},{"key":"23","unstructured":"[23] A. Krizhevsky and G. Hinton, \u201cLearning multiple layers of features from tiny images,\u201d Technical Report, University of Toronto, Toronto, Ontario, 2009."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft COCO: Common objects in context,\u201d European Conference on Computer Vision, pp.740-755, Springer, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"25","unstructured":"[25] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, \u201cScikit-learn: Machine learning in Python,\u201d Journal of Machine Learning Research, vol.12, pp.2825-2830, 2011."}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/3\/E106.A_2022VLP0004\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,4]],"date-time":"2023-03-04T03:21:25Z","timestamp":1677900085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/3\/E106.A_2022VLP0004\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2022vlp0004","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]},"article-number":"2022VLP0004"}}