The Limitations of Federated Learning in Sybil Settings

By Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh. International Symposium on Recent Advances in Intrusion Detection, 2020

567 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/52f2fceeca09116016784616f0fb94316db5e6cf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Lingjuan Lyu
2. Lichao Sun
3. Han Yu
4. Philip S. Yu
5. Xingjun Ma
6. Qiang Yang
7. Jun Zhao
8. Zhiyi Tian

Citations in the corpus

• A Robust Privacy-Preserving Federated Learning Model Against Model Poisoning Attacks (2024, methodology): “Due to maintaining parity with the compared academic literature such as [3], [5], [6], [7], [10], and [33], the logistic regression classifier model and three classification datasets: MNIST, KDDCup, and Amazon, under both IID and non-IID settings, is considered for evaluation and to ensure a fair…”
• Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, methodology): “Meanwhile, it is suggested to integrate multidisciplinary goals in the system design of FL.”
• Differential Privacy for Deep and Federated Learning: A Survey (2022, background): “In addition, using this decentralized strategy to aggregate local gradients make the FL network vulnerable to label-flipping and data poisoning attacks [124], [125], besides, it is difficult for the server to distinguish malicious from legitimate clients.”
• Biscotti: A Blockchain System for Private and Secure Federated Learning (2021, background): “Prior work has demonstrated that adversaries can attack the shared model through poisoning attacks [11], [12], [15], [16], [17], [18], [19], in which an adversary contributes adversarial updates to shared model parameters.”
• A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, background): “2016 [35] poisoning detection Evaluate the cosine similarity of the updates history.”
• FLAME: Taming Backdoors in Federated Learning (2022, methodology): “Existing works assume that X ′ i ≈ X ′ j ( ∀ i , j : 1 ≤ i , j ≤ a ) (see e.g., [22] or X ′ = X [9,51]).”