{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:48:20Z","timestamp":1766134100690,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102379"],"award-info":[{"award-number":["62102379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Recent work has shown that deep neural networks are vulnerable to backdoor attacks. In comparison with the success of backdoor-attack methods, existing backdoor-defense methods face a lack of theoretical foundations and interpretable solutions. Most defense methods are based on experience with the characteristics of previous attacks, but fail to defend against new attacks. In this paper, we propose IBD, an interpretable backdoor-detection method via multivariate interactions. Using information theory techniques, IBD reveals how the backdoor works from the perspective of multivariate interactions of features. Based on the interpretable theorem, IBD enables defenders to detect backdoor models and poisoned examples without introducing additional information about the specific attack method. Experiments on widely used datasets and models show that IBD achieves a 78% increase in average in detection accuracy and an order-of-magnitude reduction in time cost compared with existing backdoor-detection methods.<\/jats:p>","DOI":"10.3390\/s22228697","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:22:02Z","timestamp":1668115322000},"page":"8697","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["IBD: An Interpretable Backdoor-Detection Method via Multivariate Interactions"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9791-0980","authenticated-orcid":false,"given":"Yixiao","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8510-4025","authenticated-orcid":false,"given":"Xiaolei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangyi","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangzhou","family":"Xin","sequence":"additional","affiliation":[{"name":"Institute of Computer Application, China Academy of Engineering Physics, Mianyang 621900, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/TITS.2011.2160539","article-title":"Multiband image segmentation and object recognition for understanding road scenes","volume":"12","author":"Kang","year":"2011","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Al-Qizwini, M., Barjasteh, I., Al-Qassab, H., and Radha, H. (2017, January 11\u201314). Deep learning algorithm for autonomous driving using googlenet. Proceedings of the 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, USA.","DOI":"10.1109\/IVS.2017.7995703"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.iatssr.2019.11.008","article-title":"Deep learning-based image recognition for autonomous driving","volume":"43","author":"Fujiyoshi","year":"2019","journal-title":"IATSS Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.imavis.2016.03.018","article-title":"Face recognition for authentication on mobile devices","volume":"55","year":"2016","journal-title":"Image Vis. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zulfiqar, M., Syed, F., Khan, M.J., and Khurshid, K. (2019, January 24\u201325). Deep face recognition for biometric authentication. Proceedings of the IEEE 2019 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Swat, Pakistan.","DOI":"10.1109\/ICECCE47252.2019.8940725"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"47230","DOI":"10.1109\/ACCESS.2019.2909068","article-title":"BadNets: Evaluating Backdooring Attacks on Deep Neural Networks","volume":"7","author":"Gu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tang, R., Du, M., Liu, N., Yang, F., and Hu, X. (2020, January 6\u201310). An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event.","DOI":"10.1145\/3394486.3403064"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Latif, S., e Huma, Z., Jamal, S.S., Ahmed, F., Ahmad, J., Zahid, A., Dashtipour, K., Aftab, M.U., Ahmad, M., and Abbasi, Q.H. (2021). Intrusion detection framework for the internet of things using a dense random neural network. IEEE Trans. Ind. Inform., 6435\u20136444.","DOI":"10.1109\/TII.2021.3130248"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Oluwasanmi, A., Aftab, M.U., Baagyere, E., Qin, Z., Ahmad, M., and Mazzara, M. (2021). Attention Autoencoder for Generative Latent Representational Learning in Anomaly Detection. Sensors, 22.","DOI":"10.3390\/s22010123"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9325803","DOI":"10.1155\/2022\/9325803","article-title":"Small-scale and occluded pedestrian detection using multi mapping feature extraction function and Modified Soft-NMS","volume":"2022","author":"Assefa","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Oyama, T., Okura, S., Yoshida, K., and Fujino, T. (2021, January 19). Backdoor Attack on Deep Neural Networks Triggered by Fault Injection Attack on Image Sensor Interface. Proceedings of the 5th Workshop on Attacks and Solutions in Hardware Security, Virtual Event.","DOI":"10.1145\/3474376.3487287"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, B., Yao, Y., Shan, S., Li, H., Viswanath, B., Zheng, H., and Zhao, B.Y. (2019, January 19\u201323). Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP.2019.00031"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D.C., and Nepal, S. (2019, January 9\u201313). STRIP: A defence against trojan attacks on deep neural networks. Proceedings of the 35th Annual Computer Security Applications Conference, San Juan, PR, USA.","DOI":"10.1145\/3359789.3359790"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kolouri, S., Saha, A., Pirsiavash, H., and Hoffmann, H. (2020, January 14\u201319). Universal litmus patterns: Revealing backdoor attacks in cnns. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00038"},{"key":"ref_15","unstructured":"Nguyen, T.A., and Tran, A.T. (2021, January 3\u20137). WaNet-Imperceptible Warping-based Backdoor Attack. Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Doan, K., Lao, Y., Zhao, W., and Li, P. (2021, January 11\u201317). LIRA: Learnable, Imperceptible and Robust Backdoor Attacks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01175"},{"key":"ref_17","unstructured":"Chen, X., Liu, C., Li, B., Lu, K., and Song, D. (2017). Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rakin, A.S., He, Z., and Fan, D. (2020, January 14\u201319). TBT: Targeted Neural Network Attack With Bit Trojan. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01321"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, Y., Daly, R., Kim, J.S., Fallin, C., Lee, J., Lee, D., Wilkerson, C., Lai, K., and Mutlu, O. (2014, January 14\u201318). Flipping bits in memory without accessing them: An experimental study of DRAM disturbance errors. Proceedings of the International Symposium on Computer Architecture, Minneapolis, MN, USA.","DOI":"10.1109\/ISCA.2014.6853210"},{"key":"ref_20","unstructured":"Li, Y., Jiang, Y., Li, Z., and Xia, S.T. (2022). Backdoor learning: A survey. IEEE Trans. Neural Netw. Learn. Syst., 1\u201318."},{"key":"ref_21","unstructured":"Lundberg, S.M., Erion, G.G., and Lee, S. (2018). Consistent Individualized Feature Attribution for Tree Ensembles. arXiv."},{"key":"ref_22","first-page":"9259","article-title":"The Shapley Taylor Interaction Index","volume":"119","author":"Sundararajan","year":"2020","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_23","unstructured":"Zhang, H., Xie, Y., Zheng, L., Zhang, D., and Zhang, Q. (March, January 22). Interpreting Multivariate Shapley Interactions in DNNs. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W., and Tucker, A.W. (1953). Contributions to the Theory of Games, Princeton University Press.","DOI":"10.1515\/9781400881970"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Roth, A.E. (1988). The Shapley Value: Essays in Honor of Lloyd S. Shapley, Cambridge University Press.","DOI":"10.1017\/CBO9780511528446"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_27","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images. [Master\u2019s Thesis, University of Tront]."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M., and Igel, C. (2013, January 4\u20139). Detection of Traffic Signs in Real-World Images: The German Traffic Sign Detection Benchmark. Proceedings of the International Joint Conference on Neural Networks, Dallas, TX, USA. Number 1288.","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, K., Dolan-Gavitt, B., and Garg, S. (2018, January 10\u201312). Fine-pruning: Defending against backdooring attacks on deep neural networks. Proceedings of the International Symposium on Research in Attacks, Intrusions, and Defenses, Crete, Greece.","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8697\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:14:09Z","timestamp":1760145249000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":30,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228697"],"URL":"https:\/\/doi.org\/10.3390\/s22228697","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,11,10]]}}}