{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:03:51Z","timestamp":1780085031414,"version":"3.54.0"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132011"],"award-info":[{"award-number":["62132011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425201"],"award-info":[{"award-number":["62425201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472247"],"award-info":[{"award-number":["62472247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502473"],"award-info":[{"award-number":["62502473"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","doi-asserted-by":"publisher","award":["JYB2025XDXM114"],"award-info":[{"award-number":["JYB2025XDXM114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing\u2013Tianjin\u2013Hebei Natural Science Foundation Cooperation Project","award":["25JJJJC0003"],"award-info":[{"award-number":["25JJJJC0003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3690471","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T20:02:12Z","timestamp":1778011332000},"page":"5223-5238","source":"Crossref","is-referenced-by-count":0,"title":["Toward Robust Detection of Malicious Encrypted Traffic Using Only Low-Quality Training Data"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4226-9387","authenticated-orcid":false,"given":"Yuqi","family":"Qing","sequence":"first","affiliation":[{"name":"INSC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0148-2772","authenticated-orcid":false,"given":"Qilei","family":"Yin","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhao","family":"Deng","sequence":"additional","affiliation":[{"name":"INSC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2822-5952","authenticated-orcid":false,"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-0434","authenticated-orcid":false,"given":"Zhuotao","family":"Liu","sequence":"additional","affiliation":[{"name":"INSC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4152-2107","authenticated-orcid":false,"given":"Kun","family":"Sun","sequence":"additional","affiliation":[{"name":"IST, George Mason University, Fairfax, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-8517","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Zhang","sequence":"additional","affiliation":[{"name":"INSC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8776-8730","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"INSC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.106944"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2996758.2996768"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098163"},{"key":"ref4","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. ICML","author":"Arazo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616639"},{"key":"ref6","first-page":"807","article-title":"Optimized invariant representation of network traffic for detecting unseen malware variants","volume-title":"Proc. USENIX Secur.","author":"Bartos"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2025.3558545"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2025.3615592"},{"key":"ref12","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134063"},{"key":"ref14","article-title":"TrafficLLM: Enhancing large language models for network traffic analysis with generic traffic representation","author":"Cui","year":"2025","journal-title":"arXiv:2504.04222"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179464"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2026.230059"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SPW53761.2021.00009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014102"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363576"},{"key":"ref22","first-page":"3431","article-title":"Frequency domain feature based robust malicious traffic detection","volume-title":"Proc. CCS","author":"Fu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3195871"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.23080"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3545948.3545983"},{"key":"ref27","first-page":"881","article-title":"MADE: Masked autoencoder for distribution estimation","volume-title":"Proc. PMLR","author":"Germain"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref29","first-page":"1866","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proc. ICLR","author":"Goldberger"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102810"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"ref35","first-page":"10477","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume-title":"Proc. NeurIPS","author":"Hendrycks"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00079"},{"key":"ref38","first-page":"111","article-title":"The class imbalance problem: Significance and strategies","volume-title":"Proc. icARTi","author":"Japkowicz"},{"key":"ref39","first-page":"513","article-title":"AttriGuard: A practical defense against attribute inference attacks via adversarial machine learning","volume-title":"Proc. USENIX Secur.","author":"Jia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02187-4"},{"key":"ref42","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. NeurIPS","author":"Kingma"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5220\/0006105602530262"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24403"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02299-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00146"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512217"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624124"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737507"},{"key":"ref51","first-page":"14153","article-title":"Robust training under label noise by over-parameterization","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3433446"},{"key":"ref53","first-page":"855","article-title":"On the computational efficiency of training neural networks","volume-title":"Proc. NeurIPS","author":"Livni"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2876857"},{"key":"ref55","first-page":"1","article-title":"Curriculum loss: Robust learning and generalization against label corruption","volume-title":"Proc. ICLR","author":"Lyu"},{"key":"ref56","first-page":"960","article-title":"Decoupling \u2019when to update\u2019 from\u2019 \u2019how to update","volume-title":"Proc. NeurIPS","author":"Malach"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2025.3611908"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.42"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23204"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/DASC-PICom-CBDCom-CyberSciTech49142.2020.00026"},{"key":"ref61","first-page":"589","article-title":"ExecScent: Mining for new C&C domains in live networks with adaptive control protocol templates","volume-title":"Proc. USENIX Secur.","author":"Nelms"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00112-7"},{"key":"ref64","first-page":"729","article-title":"TESSERACT: Eliminating experimental bias in malware classification across space and time","volume-title":"Proc. USENIX Secur.","author":"Pendlebury"},{"key":"ref65","first-page":"4283","article-title":"Network detection of interactive $SSH$ impostors using deep learning","volume-title":"Proc. USENIX Secur.","author":"Piet"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3432404"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.23081"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23105"},{"key":"ref69","first-page":"229","article-title":"Snort-lightweight intrusion detection for networks","volume-title":"Proc. LISA","author":"Roesch"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5220\/0006639801080116"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521272"},{"key":"ref72","first-page":"607","article-title":"Subverting website fingerprinting defenses with robust traffic representation","volume-title":"Proc. USENIX Secur.","author":"Shen"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243768"},{"key":"ref75","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. ICML","author":"Song"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.9734\/ajrcos\/2025\/v18i2569"},{"key":"ref78","first-page":"1","article-title":"Training convolutional networks with noisy labels","volume-title":"Proc. ICLR","author":"Sukhbaatar"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155278"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413217"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1111\/1467-842X.00283"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150496"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2016.7590446"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2771228"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref88","volume-title":"Internet Security Report Q1 2023","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.45"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179453"},{"key":"ref91","first-page":"7597","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume-title":"Proc. NeurIPS","author":"Xia"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3603165.3607437"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24126"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3179955"},{"key":"ref95","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume-title":"Proc. NeurIPS","author":"Yao"},{"key":"ref96","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. ICML","author":"Yu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3318962"},{"key":"ref98","article-title":"Efficient GAN-based anomaly detection","author":"Zenati","year":"2018","journal-title":"arXiv:1802.06222"},{"key":"ref99","first-page":"1","article-title":"FlowRefiner: A robust traffic classification framework against label noise","volume-title":"Proc. NeurIPS","author":"Zhan"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583227"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243820"},{"key":"ref102","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref103","first-page":"1086","article-title":"Energy-based generative adversarial networks","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539314"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380090"},{"key":"ref106","first-page":"6203","article-title":"An efficient design of intelligent network data plane","volume-title":"Proc. USENIX Secur.","author":"Zhou"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11506612.pdf?arnumber=11506612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:54:59Z","timestamp":1780084499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11506612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3690471","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}