{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:44:38Z","timestamp":1782927878243,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3796701.3815914","type":"proceedings-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:40:43Z","timestamp":1782924043000},"page":"220-223","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Brief Announcement: Byzantine Machine Learning, MultiKrum and an Optimal Notion of Robustness"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6389-1767","authenticated-orcid":false,"given":"Gilles","family":"Bareilles","sequence":"first","affiliation":[{"name":"CMAP, CNRS, \u00c9cole polytechnique, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3597-6247","authenticated-orcid":false,"given":"Wassim","family":"Bouaziz","sequence":"additional","affiliation":[{"name":"Mistral AI, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-2580","authenticated-orcid":false,"given":"Julien","family":"Fageot","sequence":"additional","affiliation":[{"name":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Palaiseau, France and CMAP, CNRS, \u00c9cole polytechnique, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5041-1260","authenticated-orcid":false,"given":"El-Mahdi","family":"El-Mhamdi","sequence":"additional","affiliation":[{"name":"CMAP, CNRS, \u00c9cole polytechnique, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Dan Alistarh Zeyuan Allen-Zhu and Jerry Li. 2018. Byzantine stochastic gradient descent. In Neural Information Processing Systems. 4613\u20134623."},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 1232\u20131300","author":"Allouah Youssef","year":"2023","unstructured":"Youssef Allouah, Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafa\u00ebl Pinot, and John Stephan. 2023. Fixing by mixing: A recipe for optimal byzantine ml under heterogeneity. In International Conference on Artificial Intelligence and Statistics. PMLR, 1232\u20131300."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","first-page":"45744","DOI":"10.52202\/075280-1982","article-title":"Robust distributed learning: Tight error bounds and breakdown point under data heterogeneity","volume":"36","author":"Allouah Youssef","year":"2023","unstructured":"Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, and Geovani Rizk. 2023. Robust distributed learning: Tight error bounds and breakdown point under data heterogeneity. Advances in Neural Information Processing Systems 36 (2023), 45744\u201345776.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Gilles Bareilles Wassim Bouaziz Julien Fageot and El-Mahdi El-Mhamdi. 2026. Byzantine Machine Learning: MultiKrum and an optimal notion of robustness. doi:doi.org\/10.48550\/arXiv.2602.03899 Full version of this paper.","DOI":"10.48550\/arXiv.2602.03899"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. Number 775","author":"Baruch Moran","year":"2019","unstructured":"Moran Baruch, Gilad Baruch, and Yoav Goldberg. 2019. A Little Is Enough: Circumventing Defenses for Distributed Learning. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Number 775. Curran Associates Inc., Red Hook, NY, USA, 8635\u20138645."},{"key":"e_1_3_2_1_6_1","unstructured":"Peva Blanchard El-Mahdi El-Mhamdi Rachid Guerraoui and Julien Stainer. 2017. Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. In Neural Information Processing Systems. 118\u2013128."},{"key":"e_1_3_2_1_7_1","volume-title":"Inverting Gradient Attacks Makes Powerful Data Poisoning. Transactions on Machine Learning Research","author":"Bouaziz Wassim","year":"2025","unstructured":"Wassim Bouaziz, Nicolas Usunier, and El-Mahdi El-Mhamdi. 2025. Inverting Gradient Attacks Makes Powerful Data Poisoning. Transactions on Machine Learning Research (2025), 0. https:\/\/openreview.net\/forum?id=Lvy5MjyTh3"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2024.2391778"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585385"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616390.3618283"},{"key":"e_1_3_2_1_11_1","first-page":"0","article-title":"The notion of breakdown point. A festschrift for Erich L","volume":"157184","author":"Donoho David L","year":"1983","unstructured":"David L Donoho and Peter J Huber. 1983. The notion of breakdown point. A festschrift for Erich L. Lehmann 157184 (1983), 0.","journal-title":"Lehmann"},{"key":"e_1_3_2_1_12_1","volume-title":"The Hidden Vulnerability of Distributed Learning in Byzantium. In International Conference on Machine Learning","volume":"80","author":"El-Mhamdi El-Mahdi","year":"2018","unstructured":"El-Mahdi El-Mhamdi, Rachid Guerraoui, and S\u00e9bastien Rouault. 2018. The Hidden Vulnerability of Distributed Learning in Byzantium. In International Conference on Machine Learning, Vol. 80. 3521\u20133530."},{"key":"e_1_3_2_1_13_1","volume-title":"Collaborative learning in the jungle (decentralized, byzantine, heterogeneous, asynchronous and nonconvex learning). Advances in neural information processing systems 34","author":"El-Mhamdi El Mahdi","year":"2021","unstructured":"El Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui, Arsany Guirguis, L\u00ea-Nguy\u00ean Hoang, and S\u00e9bastien Rouault. 2021. Collaborative learning in the jungle (decentralized, byzantine, heterogeneous, asynchronous and nonconvex learning). Advances in neural information processing systems 34 (2021), 25044\u201325057."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 6284\u20136323","author":"Farhadkhani Sadegh","year":"2022","unstructured":"Sadegh Farhadkhani, Rachid Guerraoui, Oscar Villemaud, et al. 2022. An equivalence between data poisoning and byzantine gradient attacks. In International Conference on Machine Learning. PMLR, 6284\u20136323."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.06917"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"M. Garc\u00eda-M\u00e1rquez N. Rodr\u00edguez-Barroso M. V. Luz\u00f3n and F. Herrera. 2025. Improving (\u03b1 f) -Byzantine resilience in federated learning via layerwise aggregation and cosine distance. Knowledge-Based Systems 326 (Sept. 2025) 114004. doi:10.1016\/j.knosys.2025.114004","DOI":"10.1016\/j.knosys.2025.114004"},{"key":"e_1_3_2_1_17_1","volume-title":"2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138.","author":"Garc\u00eda-M\u00e1rquez Mario","year":"2025","unstructured":"Mario Garc\u00eda-M\u00e1rquez, Nuria Rodr\u00edguez-Barroso, M Victoria Luz\u00f3n, and Francisco Herrera. 2025. Improving Krum's Byzantine Resilience in Federated Learning via layerwise aggregation. In 2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_3_2_1_18_1","volume-title":"International encyclopedia of statistical science","author":"Huber Peter J","unstructured":"Peter J Huber. 2011. Robust statistics. In International encyclopedia of statistical science. Springer, 1248\u20131251."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5319","author":"Karimireddy Sai Praneeth","year":"2021","unstructured":"Sai Praneeth Karimireddy, Lie He, and Martin Jaggi. 2021. Learning from History for Byzantine Robust Optimization. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 5311\u20135319. https:\/\/proceedings.mlr.press\/v139\/karimireddy21a.html"},{"key":"e_1_3_2_1_20_1","volume-title":"Fedgreed: A byzantine-robust loss-based aggregation method for federated learning. arXiv preprint arXiv:2508.18060","author":"Kritharakis Emmanouil","year":"2025","unstructured":"Emmanouil Kritharakis, Antonios Makris, Dusan Jakovetic, and Konstantinos Tserpes. 2025. Fedgreed: A byzantine-robust loss-based aggregation method for federated learning. arXiv preprint arXiv:2508.18060 (2025), 0."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1828"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Blockchain and Trustworthy Systems. Springer, 621\u2013635","author":"Li Xiaoli","year":"2019","unstructured":"Xiaoli Li, Erxin Du, Chuan Chen, Zibin Zheng, Ting Cai, and Qiang Yan. 2019. Blockchain-based credible and privacy-preserving QoS-aware web service recommendation. In International Conference on Blockchain and Trustworthy Systems. Springer, 621\u2013635."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4328\u20134338","author":"Li Xiang","year":"2025","unstructured":"Xiang Li, Lannan Luo, and Qiang Zeng. 2025. Backdoor attacks on neural networks via one-bit flip. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4328\u20134338."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651306"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-5438-0_20"},{"key":"e_1_3_2_1_27_1","volume-title":"Miad Faezipour, and Smrity Bhatt.","author":"Saha Sajal","year":"2025","unstructured":"Sajal Saha, Moinul Sayed, Md Motiur Rahman, Miad Faezipour, and Smrity Bhatt. 2025. Resilient Federated Learning for DDoS Detection with Multi-Krum Aggregation and Anomaly Detection. In 2025 International Conference on Smart Applications, Communications and Networking (SmartNets). IEEE, 1\u20136."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Virat Shejwalkar and Amir Houmansadr. 2021. Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning. In NDSS.","DOI":"10.14722\/ndss.2021.24498"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Information and Knowledge Systems. Springer, 168\u2013175","author":"Taheri Rahim","year":"2023","unstructured":"Rahim Taheri, Farzad Arabikhan, Alexander Gegov, and Negar Akbari. 2023. Robust aggregation function in federated learning. In International Conference on Information and Knowledge Systems. Springer, 168\u2013175."},{"key":"e_1_3_2_1_30_1","volume-title":"SpectralKrum: A Spectral-Geometric Defense Against Byzantine Attacks in Federated Learning. arXiv preprint arXiv.2512.11760","author":"Tripathi Aditya","year":"2025","unstructured":"Aditya Tripathi, Karan Sharma, Rahul Mishra, and Tapas Kumar Maiti. 2025. SpectralKrum: A Spectral-Geometric Defense Against Byzantine Attacks in Federated Learning. arXiv preprint arXiv.2512.11760 (2025), 0."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference","volume":"22","author":"Tu Jiyuan","year":"2021","unstructured":"Jiyuan Tu, Weidong Liu, Xiaojun Mao, and Xi Chen. 2021. Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference. Journal of Machine Learning Research 22, 84 (2021), 1\u201367.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_32_1","volume-title":"Attack of the tails: Yes, you really can backdoor federated learning. Advances in neural information processing systems 33","author":"Wang Hongyi","year":"2020","unstructured":"Hongyi Wang, Kartik Sreenivasan, Shashank Rajput, Harit Vishwakarma, Saurabh Agarwal, Jy-yong Sohn, Kangwook Lee, and Dimitris Papailiopoulos. 2020. Attack of the tails: Yes, you really can backdoor federated learning. Advances in neural information processing systems 33 (2020), 16070\u201316084."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of The 35th Uncertainty in Artificial Intelligence Conference. PMLR, 261\u2013270","author":"Xie Cong","year":"2020","unstructured":"Cong Xie, Oluwasanmi Koyejo, and Indranil Gupta. 2020. Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation. In Proceedings of The 35th Uncertainty in Artificial Intelligence Conference. PMLR, 261\u2013270."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning. PMLR, 5650\u20135659","author":"Yin Dong","year":"2018","unstructured":"Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter Bartlett. 2018. Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. In Proceedings of the 35th International Conference on Machine Learning. PMLR, 5650\u20135659."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.25"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20903"}],"event":{"name":"PODC '26: ACM Symposium on Principles of Distributed Computing","location":"Egham United Kingdom","acronym":"PODC '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGACT ACM Special Interest Group on Algorithms and Computation Theory"]},"container-title":["Proceedings of the ACM Symposium on Principles of Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3796701.3815914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:50:16Z","timestamp":1782924616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3796701.3815914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":36,"alternative-id":["10.1145\/3796701.3815914","10.1145\/3796701"],"URL":"https:\/\/doi.org\/10.1145\/3796701.3815914","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-07-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}