AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning

• URL: http://arxiv.org/abs/2509.22873v2
• Date: Tue, 30 Sep 2025 04:36:41 GMT
• Title: AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
• Authors: Aashnan Rahman, Abid Hasan, Sherajul Arifin, Faisal Haque Bappy, Tahrim Hossain, Tariqul Islam, Abu Raihan Mostofa Kamal, Md. Azam Hossain,
• Abstract summary: Federated learning (FL) enables privacy-preserving model training by keeping data decentralized.<n>It remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model.<n>We introduce AntiFLipper, a novel and computationally efficient defense against multi-class label-flipping attacks in FL.
• Score: 2.699539310040651
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their simplicity, these attacks can severely degrade model performance, and defending against them remains challenging. We introduce AntiFLipper, a novel and computationally efficient defense against multi-class label-flipping attacks in FL. Unlike existing methods that ensure security at the cost of high computational overhead, AntiFLipper employs a novel client-side detection strategy, significantly reducing the central server's burden during aggregation. Comprehensive empirical evaluations across multiple datasets under different distributions demonstrate that AntiFLipper achieves accuracy comparable to state-of-the-art defenses while requiring substantially fewer computational resources in server side. By balancing security and efficiency, AntiFLipper addresses a critical gap in existing defenses, making it particularly suitable for resource-constrained FL deployments where both model integrity and operational efficiency are essential.

Related papers

• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning [0.696125353550498]
  Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains.<n>We present FuSeFL, a fully secure and scalable FL scheme designed for cross-silo settings.
  arXiv  Detail & Related papers  (2025-07-18T00:50:44Z)
• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• Sparsification Under Siege: Defending Against Poisoning Attacks in Communication-Efficient Federated Learning [9.911465831373423]
  Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy.<n>It faces significant challenges in communication efficiency and vulnerability to poisoning attacks.<n>We propose FLARE, a novel federated learning framework that integrates sparse index mask inspection and model update sign similarity analysis.
  arXiv  Detail & Related papers  (2025-04-30T14:59:13Z)
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning [69.72249695674665]
  We propose a robust test-time prompt tuning (R-TPT) for vision-language models (VLMs)<n>R-TPT mitigates the impact of adversarial attacks during the inference stage.<n>We introduce a plug-and-play reliability-based weighted ensembling strategy to strengthen the defense.
  arXiv  Detail & Related papers  (2025-04-15T13:49:31Z)
• Byzantine-Robust Federated Learning Using Generative Adversarial Networks [1.4091801425319963]
  Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, but its robustness is threatened by Byzantine behaviors such as data and model poisoning.<n>We present a defense framework that addresses these challenges by leveraging a conditional generative adversarial network (cGAN) at the server to synthesize representative data for validating client updates.<n>This approach eliminates reliance on external datasets, adapts to diverse attack strategies, and integrates seamlessly into standard FL.
  arXiv  Detail & Related papers  (2025-03-26T18:00:56Z)
• 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)
• 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)
• SPFL: A Self-purified Federated Learning Method Against Poisoning Attacks [12.580891810557482]
  Federated learning (FL) is attractive for pulling privacy-preserving distributed training data. We propose a self-purified FL (SPFL) method that enables benign clients to exploit trusted historical features of locally purified model. We experimentally demonstrate that SPFL outperforms state-of-the-art FL defenses against various poisoning attacks.
  arXiv  Detail & Related papers  (2023-09-19T13:31:33Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Challenges and approaches for mitigating byzantine attacks in federated learning [6.836162272841266]
  Federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Despite the promising prospect, byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. We propose a new byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat.
  arXiv  Detail & Related papers  (2021-12-29T09:24:05Z)

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.