Robust federated learning with attack-adaptive aggregation
Abstract
HKUST Electronic Theses Robust federated learning with attack-adaptive aggregation by Wan Ching Pui thesis 2021 1 online resource (x, 50 pages) : illustrations (chiefly color) In this thesis, we discuss a data-driven approach to defend adversarial attacks in federated learning.…Read more ›
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The attention-based neural network defense trains a separate neural network on simulated model updates under various backdoor attacks to learn the potential vulnerability of the global model against different backdoor attacks.
“The central server simulates the WFL tasks under various types of backdoor attacks. Then, the simulated model updates are collected to train a separate neural network model, which learns the potential vulnerability of the global model against different backdoor attacks.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [219]
The attention-based defense requires all possible backdoor attack patterns to be trained in the server before implementation, and the aggregator requires access to single local updates, risking participant privacy.
“The major problem of this defense method is that to distinguish the malicious updates, all possible backdoor attack patterns must be trained in the server before implementation. During the detection, the aggregator requires access to single local updates. Thus, the privacy of the participant is at risk of leaking.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [219]
In the attention-based defense, an alignment score closer to +1 indicates a more likely benign update, while a score close to -1 indicates a likely adversary update.
“If the alignment score 𝑠 𝑖 is closer to + 1 , 𝑝 𝑖 is more likely to be a benign update. On the other hand, if 𝑠 𝑖 is close to -1 , 𝑝 𝑖 is likely to be an adversary update.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [219]
The attention-based method shows better defense performance than traditional median-based aggregation and residual-based re-weighting aggregation.
“This method shows better defense performance than traditional median-based aggregation and residual-based re-weighting aggregation.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [219]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 6× · see citing works
“In the CIFAR-10 and the Tiny-ImageNet task, the backdoor was not ’forgotten’ since the ResNet-18 had more capacity to learn both the main task and the backdoor.”
InfluentialGradient-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 · see citing works
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · see citing works
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · see citing works
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863 · see citing works
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 1× · see citing works
“(2019) suggested that adding the differential privacy (Abadi et al., 2016) can improve robustness against certain attacks.”
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545 · see citing works
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023 · cited 1× · see citing works
“In [Li et al. , 2020], their approach detects attackers by learning a variational autoencoder on randomly sampled coordinates of the unbiased model updates obtained in the centralized training setting.”
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · see citing works
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435 · see citing works
Measuring the Effects of Non-Identical Data Distribution for Federated Visual ClassificationPreprint
Hsu, T., Qi, & Brown, M. (2019) · arXiv.org · doi:10.48550/arxiv.1909.06335 · Cited by 1,757 · see citing works
How to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · see citing works
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331 · cited 1× · see citing works
“(2018) suggested that the label flipping attack (Biggio et al., 2012), which changes the label of a certain class, can already be an effective attack if there are no defenses.”
Federated Multi-Task LearningPreprint
Smith, V., Chiang, C.-K., Sanjabi, M., & Talwalkar, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10467 · Cited by 1,282 · see citing works
GradientBased Learning Applied to Document Recognition
Haykin, S., & Kosko, B. (2009) · Institute of Electrical and Electronics Engineers eBooks · doi:10.1109/9780470544976.ch9 · Cited by 1,208 · cited 2× · see citing works
“We compare our approach with existing aggregation rules on federated learning tasks: MNIST [LeCun et al. , 1998] classification, CIFAR-10 [Krizhevsky et al. , 2009] classifi-cation, Tiny-ImageNet classification, and IMDb [Maas et al. , 2011] sentiment analysis.”
Federated Learning for Mobile Keyboard Prediction
Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., Eichner, H., Kiddon, C., & Ramage, D. (2018) · arXiv · doi:10.48550/arxiv.1811.03604 · Cited by 1,148 · see citing works
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130 · see citing works
Differentially Private Federated Learning: A Client Level Perspective
Geyer, R. C., Klein, T., & Nabi, M. (2017) · arXiv · doi:10.48550/arxiv.1712.07557 · Cited by 1,052 · cited 1× · see citing works
“The defense on federated learning can be categorized in terms of robustness, privacy (Geyer et al., 2017; Hardy et al., 2017; Bhowmick et al., 2018), and security (Bonawitz et al.”
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017) · arXiv · doi:10.48550/arxiv.1712.05526 · Cited by 1,039 · cited 2× · see citing works
“For example, with the backdoor attack (Chen et al., 2017), the attacker can locally assign a ‘horse’ label to the images of the automobiles manufactured by a certain brand.”
Robust Aggregation for Federated Learning
Pillutla, K., Kakade, S. M., & Harchaoui, Z. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3153135 · Cited by 947 · see citing works
Federated Learning with Matched AveragingPreprint
Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., & Khazaeni, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.06440 · Cited by 725 · see citing works
Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, . (2019) · Annual Computer Security Applications Conference · doi:10.1145/3359789.3359790 · Cited by 719 · see citing works
Analyzing Federated Learning through an Adversarial Lens
Bhagoji, A. N., Chakraborty, S., Mittal, P., & Calo, S. (2018) · arXiv · doi:10.48550/arxiv.1811.12470 · Cited by 703 · see citing works
Hardy, S., Henecka, W., Ivey-Law, H., Nock, R., Patrini, G., Smith, G., & Thorne, B. (2017) · arXiv · doi:10.48550/arxiv.1711.10677 · Cited by 431 · cited 1× · see citing works
“The defense on federated learning can be categorized in terms of robustness, privacy (Geyer et al., 2017; Hardy et al., 2017; Bhowmick et al., 2018), and security (Bonawitz et al.”
Attack of the tails: Yes, you really can backdoor federated learning
Wang, H., Sreenivasan, K., Rajput, S., Vishwakarma, H., Agarwal, S., Sohn, J.-Y., Lee, K., & Papailiopoulos, D. (2020) · arXiv · doi:10.48550/arxiv.2007.05084 · Cited by 406 · see citing works
Mitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385 · see citing works
Can You Really Backdoor Federated Learning?
Sun, Z., Kairouz, P., Suresh, A. T., & McMahan, H. B. (2019) · arXiv · doi:10.48550/arxiv.1911.07963 · Cited by 348 · see citing works
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks
Chen, H., Fu, C., Zhao, J., & Koushanfar, F. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/647 · Cited by 314 · see citing works
Protection Against Reconstruction and Its Applications in Private Federated LearningPreprint
Bhowmick, A., Duchi, J. C., Freudiger, J., Kapoor, G., & Rogers, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00984 · Cited by 261 · cited 1× · see citing works
“The defense on federated learning can be categorized in terms of robustness, privacy (Geyer et al., 2017; Hardy et al., 2017; Bhowmick et al., 2018), and security (Bonawitz et al.”
Learning to Detect Malicious Clients for Robust Federated LearningPreprint
Li, S., Cheng, Y. J., Wang, W., Liu, Y., & Chen, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00211 · Cited by 202 · see citing works
A Little Is Enough: Circumventing Defenses For Distributed LearningPreprint
Baruch, M., Baruch, G., & Goldberg, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.06156 · Cited by 184 · see citing works
On the Byzantine Robustness of Clustered Federated Learning
Sattler, F., Müller, K., Wiegand, T., & Samek, W. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054676 · Cited by 184 · see citing works
Sever: A Robust Meta-Algorithm for Stochastic OptimizationPreprint
Diakonikolas, I., Kamath, G., Kane, D. M., Li, J. Z., Steinhardt, J., & Stewart, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.02815 · Cited by 162 · see citing works
Byzantine-Robust Federated Machine Learning through Adaptive Model AveragingPreprint
Muñoz-González, L., Co, K. T., & Lupu, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05125 · Cited by 153 · see citing works
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations
Dumford, J., & Scheirer, W. J. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304875 · Cited by 102 · see citing works
Distilled One-Shot Federated LearningPreprint
Zhou, Y., Pu, G., Ma, X., Li, X., & Wu, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07999 · Cited by 79 · see citing works
Attack-Resistant Federated Learning with Residual-based ReweightingPreprint
Fu, S., Xie, C., Li, B., & Chen, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11464 · Cited by 78 · see citing works
DETOX: A redundancy-based framework for faster and more robust gradient aggregation
Rajput, S., Wang, H., Charles, Z., & Papailiopoulos, D. (2019) · arXiv · doi:10.48550/arxiv.1907.12205 · Cited by 72 · cited 1× · see citing works
“, 2018b) and DETOX (Rajput et al., 2019) use coding theory to partition data over clients to ensure perfect robustness at the expense of losing data privacy.”
Generalized Weiszfeld Algorithms for Lq Optimization
Aftab, K., Hartley, R. I., & Trumpf, J. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2353625 · Cited by 60 · cited 1× · see citing works
“(2019) suggested a secure implementation of the Geometric median aggregation rule with Weiszfeld’s algorithm (Aftab et al., 2014).”
Zeno: Byzantine-suspicious stochastic gradient descentPreprint
Xie, C., Koyejo, O., & Gupta, I. (2018) · arXiv.org · doi:10.48550/arxiv.1805.10032 · Cited by 48 · see citing works
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based AlgorithmsPreprint
Chen, X., Chen, T., Sun, H., Wu, Z. S., & Hong, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01736 · Cited by 41 · see citing works
Okuno, A., Hada, T., & Shimodaira, H. (2018) · International Conference on Machine Learning · doi:10.48550/arxiv.1802.04630 · Cited by 15
The Hidden Vulnerability of Distributed Learning in Byzantium
Mhamdi, E. M. E., Guerraoui, R., & Rouault, S. (2018) · arXiv · doi:10.48550/arxiv.1802.07927
Flagged first, then by citations
8 of the 54 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
Huang, W., Ye, M., Shi, Z., Wan, G., He, L., Du, B., & Yang, Q. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3418862 · Cited by 251 · see citing works
“2) Statistics Distribution Tolerance: A handful of robust aggregation schemes focus on constructing diverse statistical criteria to select the circumvent the evil clients [44], [268], [269], [275].”
BackgroundWan, Y., Qu, Y., Ni, W., Xiang, Y., Gao, L., & Hossain, E. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3361451 · Cited by 152 · see citing works
“4) Defense Using Attention-Based Neural Networks: In [219], the focus is on training an attention-based neural network.”
MethodNguyen, T. D., Nguyen, T., Nguyen, P. L., Pham, H. H., Doan, K. D., & Wong, K.-S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107166 · Cited by 130 · see citing works
FedCorr: Multi-Stage Federated Learning for Label Noise Correction
Xu, J., Chen, Z., Quek, T. Q. S., & Chong, K. F. E. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00994 · Cited by 133 · see citing works
Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective
Huang, G., Chen, X., Ouyang, T., Ma, Q., Chen, L., & Zhang, J. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3194198 · Cited by 32 · see citing works
“In response to the backdoor attack [26], we can refer to three state-of-art defense mechanisms to defend it from the perspective of certified defense [27], validation datasets detection [28] and robust aggregation [29], respectively.”
BackgroundEnhancing federated learning robustness through randomization and mixture
Nabavirazavi, S., Taheri, R., & Iyengar, S. S. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.04.009 · Cited by 30 · see citing works
FLAD: Byzantine-Robust Federated Learning Based on Gradient Feature Anomaly Detection
Tang, P., Zhu, X., Qiu, W., Huang, Z. R., Mu, Z., & Li, S. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3542437 · Cited by 23 · see citing works
“Therefore, numerous methods focus on either improving local gradients sent to the server or preprocessing local gradients and clipping global gradients at the server, such as Byrd-SAGA [11], signSGD [28], FLTrust [6], CRFL [7] and Attack-adaptive Aggregation [29].”
RaSA: Robust and Adaptive Secure Aggregation for Edge-Assisted Hierarchical Federated Learning
Wang, L., Huang, M., Zhang, Z., Li, M., Wang, J., & Gai, K. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3559411 · Cited by 16 · see citing works
“Nevertheless, existing weight updating algorithms [2], [11], [12] fail to meet privacy-preserving requirements, as clients send plaintext gradients or local data amounts to the PS responsible for updating the aggregation weights.”
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
Zhang, Z., Su, Q., & Sun, X. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.25 · Cited by 16 · see citing works
Non trust detection of decentralized federated learning based on historical gradient
Chen, Y., Li, L., & Gao, W. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105888 · Cited by 12 · see citing works
Robust federated learning with voting and scaling
Liang, X.-Y., Zhang, H., Tang, W., & Min, F. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.11.015 · Cited by 7 · see citing works
AIFL: Ensuring Unlinkable Anonymity and Robust Incentive in Cross-Device Federated Learning
Chen, X., Gao, Y., & Deng, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3417003 · Cited by 7 · see citing works
Data Distribution-Aware Model Aggregation for non-IID Data in a Federated Learning Framework
Kushwaha, D., Mehrotra, A., & Hegde, R. M. (2024) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms59830.2024.10575887 · Cited by 6 · see citing works
Is Performance Fairness Achievable in Presence of Attackers Under Federated Learning?
Gupta, A., Markowsky, G., & Das, S. K. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230365 · Cited by 4 · see citing works
Robust Combination of Distributed Gradients Under Adversarial Perturbations
Kim, K. I. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00035 · Cited by 2 · see citing works
“3 is general and it includes other algorithms including Wan and Chen’s robust federated learning approach [34] as a special case.”
BackgroundMethodInfluentialMiao, Q., Sun, W. Y., Zhu, D., et al. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3656886 · Cited by 1 · see citing works
“…against these attacks already exist, including mitigating the impact of malicious client updates on the global model through robust aggregation [50], [51], identifying and removing malicious updates via trigger-based detection [52], [53], and reducing the effectiveness of malicious updates…”
Model Backdoor Attack on Federated Learning Based on Parameter Analysis
Wang, B., Yan, Y., Zhang, M., Wang, W., & Yao, H. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3664908 · Cited by 2 · see citing works
“Wan and Chen [34] trained an attention-based neural network to collect model updates under different types of backdoor attacks in a simulated federated learning task, learning the potential vulnerabilities of the global model to backdoor attacks in a self-supervised manner to enhance defense…”
Xu, J., Tong, X., & Huang, S. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838792 · Cited by 2 · see citing works
“Similar method has also been used in [29] for weighted average since the exponent exp ( − τ · d i ) can never reach 0 and it can be problematic when corrupted gradient has extremely large magnitude.”
MethodAnalog Over-the-Air Federated Learning With Real-World Data
Chen, Z., Li, Z.-S., & Xu, J.-Y. (2022) · 2022 IEEE International Conference on Sensing, Communication, and Networking (SECON Workshops) · doi:10.1109/seconworkshops56311.2022.9926339 · Cited by 1 · see citing works
“To improve the robustness of the FL, multiple works have explored the techniques via client scheduling [17], model aggregation [18], personalization [19] and optimizations at both server [4], [14] and client side [20].”
MethodExploring Federated Learning: The Framework, Applications, Security & Privacy
Saha, A., Ali, L., Rahman, R., Monir, M. F., & Ahmed, T. (2024) · IEEE International Black Sea Conference on Communications and Networking · doi:10.1109/blackseacom61746.2024.10646291
RAID: A Reputation-Based Aggregation for Intrusion Detection in Federated Learning
Parvizi, N., Saha, S., & Shahriar, N. (2026) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc65079.2026.11366587
“Adaptive, data-driven defenses are also emerging, such as using neural networks to identify vulnerable regions [12] or Multi-Armed Bandit models to dynamically choose aggregation rules [13].”
Gao, Y.-T., Chen, X., Deng, H., et al. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3714152
“We evaluate our CVFL-Pro using the LetNet and ResNet-18 models [28] in datasets MNIST [29], CIFAR-10 [30], and CIFAR-100 with IID and Non-IID data.”
Aggressive, Imperceptible, or Both: Architecture-Aware Hybrid Byzantines in Federated Learning
Özfatura, E., Özfatura, K., Buyukates, B., Coşkuner, M., Küpçü, A., & Gündüz, D. (2026) · IEEE European Symposium on Security and Privacy · doi:10.1109/eurosp68448.2026.00052
SiftFL: Scheduling-Based Robust Backdoor Detection in Federated Learning
Hashem, E., Felemban, M., Mahmood, S., & Barnawi, A. Y. (2026) · IEEE Access · doi:10.1109/access.2026.3727396
“Defenses during the aggregation phase modify the aggregation rule itself to reduce or reject malicious updates [14], [17], [39], [44], [74], [75], [76], [77], [78].”
- Authors
- Wan, C. P.
- Corresponding author
- Wan, Ching Pui
- Published
- 2021-01-01
- OpenAlex
- W4220990555
- Cited by
- 24
- References
- 54
- Citations by year
- 2026: 6 · 2025: 2 · 2024: 6 · 2023: 4 · 2022: 6
- Type
- dissertation
- Language
- en
- Open access
- closed
- Locations
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- federated learning, robustness, adversarial attacks, model aggregation
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
