STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

• URL: http://arxiv.org/abs/2608.14861v1
• Date: Fri, 14 Aug 2026 19:55:24 GMT
• Title: STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation
• Abstract summary: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision.<n>We propose a novel defense framework against targeted poisoning attacks with Spatial-Temporal Analysis and Robust aggregation for FL (STAR-FL)
• Score: 2.8231278244044273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existing defense techniques: (1) accurately distinguishing between benign and malicious model updates and (2) effectively mitigating the influence of poisoned model updates during model aggregation. To address these challenges, we propose a novel defense framework against targeted poisoning attacks with Spatial-Temporal Analysis and Robust aggregation for FL (STAR-FL). First, we employ spatial-temporal clustering to identify and remove potentially malicious updates from the FL training process. Second, we adjust the learning rate during aggregation to mitigate the impact of any malicious updates that evade detection. Third, we conduct extensive experiments across multiple benchmark datasets to evaluate the spatial-temporal analysis and robust aggregation in STAR-FL. Experimental results demonstrate their synergistic effect in enabling STAR-FL to effectively protect FL and consistently outperform state-of-the-art defenses against targeted poisoning attacks, significantly reducing Attack Success Rates (ASRs). The source code is available at https://github.com/mlsysx/STAR-FL.

Related papers

• Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice [50.84321144889696]
  Federated learning (FL) has attracted substantial attention in both academia and industry.<n>But its practical security posture remains poorly understood.<n>This paper revisits FL security from a measurement perspective.
  arXiv  Detail & Related papers  (2026-03-21T03:19:05Z)
• Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning [49.68790647579509]
  Federated Ranking Learning (FRL) is a state-of-the-art FL framework that stands out for its communication efficiency and resilience to poisoning attacks.<n>We introduce a novel local model poisoning attack against FRL, namely the Vulnerable Edge Manipulation (VEM) attack.<n>Our attack achieves an overall 53.23% attack impact and is 3.7x more impactful than existing methods.
  arXiv  Detail & Related papers  (2025-03-12T00:38:14Z)
• Federated Learning for Anomaly Detection in Energy Consumption Data: Assessing the Vulnerability to Adversarial Attacks [0.8576354642891824]
  Anomaly detection is crucial in the energy sector to identify irregular patterns indicating equipment failures, energy theft, or other issues.<n> Federated Learning (FL) has been gaining popularity as it enables distributed learning without sharing local data.<n>This paper assesses the vulnerability of FL-based anomaly detection in energy data to adversarial attacks.
  arXiv  Detail & Related papers  (2025-02-07T16:08:20Z)
• Formal Logic-guided Robust Federated Learning against Poisoning Attacks [6.997975378492098]
  Federated Learning (FL) offers a promising solution to the privacy concerns associated with centralized Machine Learning (ML) FL is vulnerable to various security threats, including poisoning attacks, where adversarial clients manipulate the training data or model updates to degrade overall model performance. We present a defense mechanism designed to mitigate poisoning attacks in federated learning for time-series tasks.
  arXiv  Detail & Related papers  (2024-11-05T16:23:19Z)
• Celtibero: Robust Layered Aggregation for Federated Learning [0.0]
  We introduce Celtibero, a novel defense mechanism that integrates layered aggregation to enhance robustness against adversarial manipulation. We demonstrate that Celtibero consistently achieves high main task accuracy (MTA) while maintaining minimal attack success rates (ASR) across a range of untargeted and targeted poisoning attacks.
  arXiv  Detail & Related papers  (2024-08-26T12:54:00Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning [98.43475653490219]
  Federated learning (FL) is susceptible to poisoning attacks. FreqFed is a novel aggregation mechanism that transforms the model updates into the frequency domain. We demonstrate that FreqFed can mitigate poisoning attacks effectively with a negligible impact on the utility of the aggregated model.
  arXiv  Detail & Related papers  (2023-12-07T16:56:24Z)
• Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach [65.2993866461477]
  This paper proposes a data-agnostic, model poisoning attack on Federated Learning (FL) The attack requires no knowledge of FL training data and achieves both effectiveness and undetectability. Experiments show that the FL accuracy drops gradually under the proposed attack and existing defense mechanisms fail to detect it.
  arXiv  Detail & Related papers  (2023-11-30T12:19:10Z)
• Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks [0.45687771576879593]
  This research is the earliest attempt to study, analyze and present the impact of data poisoning attacks in SplitFed Learning (SFL) We propose three kinds of novel attack strategies namely untargeted, targeted and distance-based attacks for SFL. We test the proposed attack strategies for two different case studies on Electrocardiogram signal classification and automatic handwritten digit recognition.
  arXiv  Detail & Related papers  (2023-07-04T00:37:12Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.