SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors

• URL: http://arxiv.org/abs/2606.22700v1
• Date: Sun, 21 Jun 2026 22:34:34 GMT
• Title: SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors
• Abstract summary: Federated Learning (FL) enables collaborative model training without sharing raw data.<n>It is vulnerable to backdoor attacks, where malicious clients embed hidden triggers into local training data to manipulate model predictions.<n>We propose SCRUB-FL, a two-phase solution for post-training backdoor removal in FL.
• Score: 9.273743530407977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising paradigm for privacy-sensitive applications. However, its decentralized nature makes it inherently vulnerable to backdoor attacks, where malicious clients embed hidden triggers into local training data to manipulate model predictions. Existing defenses mainly operate during before and during aggregation cannot fully eliminate backdoor behaviors that persist in the converged global model. Moreover, the effectiveness of post-training sanitization is often limited by the server's lack of knowledge of trigger patterns or poisoned clients after convergence, resulting in residual backdoor behaviors or accuracy degradation due to neuron entanglement. To address this limitation, we propose SCRUB-FL (Sanitizing and Cleansing Representations via Unlearning of Backdoors), a two-phase solution for post-training backdoor removal in FL. During training, clients identify suspicious samples using spectral analysis and activation clustering, then train lightweight Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) models to capture trigger-related distributions. The generator parameters are aggregated server-side to construct a global representation of suspicious patterns without exposing raw data. After convergence, the server synthesizes trigger-approximating samples and applies machine unlearning to erase the trigger-target association by redistributing predictions toward a uniform distribution. Experimental evaluations on CIFAR-10 and GTSRB across three attack types and up to 40% malicious participation demonstrate that SCRUB-FL reduces the backdoor attack success rate to as low as 3.88% while maintaining over 91% normal task accuracy, outperforming state-of-the-art defenses without requiring prior trigger knowledge or a large clean proxy dataset at the server.

Related papers

• FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning [15.911410230033816]
  Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models.<n>In this paper, we propose Pre-Training Backdoor Mitigation for Federated Learning.<n>It proactively filters poisoned data on the client side before model training in a federated learning environment.
  arXiv  Detail & Related papers  (2026-03-30T16:56:38Z)
• Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models [74.1970982768771]
  We show that well-established data-poisoning pipelines can successfully implant backdoors into MDLMs.<n>We introduce a backdoor defense framework for MDLMs named DiSP (Diffusion Self-Purification)
  arXiv  Detail & Related papers  (2026-02-24T15:47:52Z)
• Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective [19.40077533912822]
  This paper investigates a more pervasive and insidious threat: textitbackdoor vulnerabilities from low-concentration poisoned data distributed across datasets of benign clients.<n>Our findings highlight an urgent need for new defense mechanisms tailored to the realities of modern, decentralized data ecosystems.
  arXiv  Detail & Related papers  (2026-02-17T15:54:45Z)
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version) [58.595691399741646]
  Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs)<n>This setup enables SL to leverage server capacities without sharing data, making it highly effective in resource-constrained environments dealing with sensitive data.<n>We present ZORRO, a private, verifiable, and robust SL defense scheme.
  arXiv  Detail & Related papers  (2025-09-11T18:44:09Z)
• BURN: Backdoor Unlearning via Adversarial Boundary Analysis [73.14147934175604]
  Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality.<n>We propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification.
  arXiv  Detail & Related papers  (2025-07-14T17:13:06Z)
• InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning [36.56302680556252]
  We introduce InverTune, the first backdoor defense framework for multimodal models under minimal attacker assumptions.<n>InverTune effectively identifies and removes backdoor artifacts through three key components, achieving robust protection against backdoor attacks.<n> Experimental results show that InverTune reduces the average attack success rate (ASR) by 97.87% against the state-of-the-art (SOTA) attacks.
  arXiv  Detail & Related papers  (2025-06-14T09:08:34Z)
• Backdoor Cleaning without External Guidance in MLLM Fine-tuning [76.82121084745785]
  Believe Your Eyes (BYE) is a data filtering framework that leverages attention entropy patterns as self-supervised signals to identify and filter backdoor samples.<n>It achieves near-zero attack success rates while maintaining clean-task performance.
  arXiv  Detail & Related papers  (2025-05-22T17:11:58Z)
• Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning [7.808916974942399]
  heterogeneous edge devices produce diverse, non-independent, and identically distributed (non-IID) data.<n>We propose a novel representative-attention-based defense mechanism, named FeRA, to distinguish benign from malicious clients.<n>Our evaluation demonstrates FeRA's robustness across various FL scenarios, including challenging non-IID data distributions typical of edge devices.
  arXiv  Detail & Related papers  (2025-05-15T13:44:32Z)
• Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations [50.1394620328318]
  Existing backdoor attacks mainly focus on balanced datasets. We propose an effective backdoor attack named Dynamic Data Augmentation Operation (D$2$AO) Our method can achieve the state-of-the-art attack performance while preserving the clean accuracy.
  arXiv  Detail & Related papers  (2024-10-16T18:44:22Z)
• Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
  Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples. We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
  arXiv  Detail & Related papers  (2023-09-14T03:48:27Z)
• 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)
• CrowdGuard: Federated Backdoor Detection in Federated Learning [39.58317527488534]
  This paper presents a novel defense mechanism, CrowdGuard, that effectively mitigates backdoor attacks in Federated Learning. CrowdGuard employs a server-located stacked clustering scheme to enhance its resilience to rogue client feedback. The evaluation results demonstrate that CrowdGuard achieves a 100% True-Positive-Rate and True-Negative-Rate across various scenarios.
  arXiv  Detail & Related papers  (2022-10-14T11:27:49Z)

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.