Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution

• URL: http://arxiv.org/abs/2412.20476v2
• Date: Tue, 30 Sep 2025 15:49:22 GMT
• Title: Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
• Authors: Yao Tong, Weijun Li, Xuanli He, Haolan Zhan, Qiongkai Xu,
• Abstract summary: Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace.<n>We propose Guided Module Substitution (GMS), an effective retraining-free method based on guided merging of the victim model with just a single proxy model.<n>GMS significantly outperforms even the strongest defense baseline, particularly against challenging attacks like LWS.
• Score: 28.661437014249213
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet underexplored challenge arises when such backdoors are discovered after model deployment, making retraining-required defenses less desirable due to computational costs and data constraints. In this work, we propose Guided Module Substitution (GMS), an effective retraining-free method based on guided merging of the victim model with just a single proxy model. Unlike prior ad-hoc merging defenses, GMS uses a guided trade-off signal between utility and backdoor to selectively replaces modules in the victim model. GMS offers four desirable properties: (1) robustness to the choice and trustworthiness of the proxy model, (2) applicability under inaccurate data knowledge, (3) stability across hyperparameters, and (4) transferability across different attacks. Extensive experiments on encoder models and decoder LLMs demonstrate the strong effectiveness of GMS. GMS significantly outperforms even the strongest defense baseline, particularly against challenging attacks like LWS.

Related papers

• Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models [62.87838888016534]
  Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets.<n>Backdoor attacks against GFMs are non-trivial due to three key challenges.<n>We propose GFM-BA, a novel Backdoor Attack model against Graph Foundation Models.
  arXiv  Detail & Related papers  (2025-11-22T08:52:09Z)
• MARS: A Malignity-Aware Backdoor Defense in Federated Learning [51.77354308287098]
  Recently proposed state-of-the-art (SOTA) attack, 3DFed, uses an indicator mechanism to determine whether backdoor models have been accepted by the defender.<n>We propose a Malignity-Aware backdooR defenSe (MARS) that leverages backdoor energy to indicate the malicious extent of each neuron.<n>Experiments demonstrate that MARS can defend against SOTA backdoor attacks and significantly outperforms existing defenses.
  arXiv  Detail & Related papers  (2025-09-21T14:50:02Z)
• DUP: Detection-guided Unlearning for Backdoor Purification in Language Models [6.726081307488787]
  DUP (Detection-guided Unlearning for Purification) is a framework that integrates backdoor detection with unlearning-based purification.<n>Based on the detection results, we purify the model through a parameter-efficient unlearning mechanism.<n>Our code is available at https://github.com/ManHu2025/DUP.
  arXiv  Detail & Related papers  (2025-08-03T08:12:21Z)
• Graph Representation-based Model Poisoning on Federated Large Language Models [3.5233863453805143]
  Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy.<n>This article first reviews recent advancements in model poisoning techniques and existing defense mechanisms for FedLLMs, underscoring critical limitations.<n>The article further investigates graph representation-based model poisoning (GRMP), an emerging attack paradigm that exploits higher-order correlations among benign client gradients to craft malicious updates indistinguishable from legitimate ones.
  arXiv  Detail & Related papers  (2025-07-02T13:20:52Z)
• 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)
• No Query, No Access [50.18709429731724]
  We introduce the textbfVictim Data-based Adrial Attack (VDBA), which operates using only victim texts.<n>To prevent access to the victim model, we create a shadow dataset with publicly available pre-trained models and clustering methods.<n>Experiments on the Emotion and SST5 datasets show that VDBA outperforms state-of-the-art methods, achieving an ASR improvement of 52.08%.
  arXiv  Detail & Related papers  (2025-05-12T06:19:59Z)
• Identify Backdoored Model in Federated Learning via Individual Unlearning [7.200910949076064]
  Backdoor attacks present a significant threat to the robustness of Federated Learning (FL) We propose MASA, a method that utilizes individual unlearning on local models to identify malicious models in FL. To the best of our knowledge, this is the first work to leverage machine unlearning to identify malicious models in FL.
  arXiv  Detail & Related papers  (2024-11-01T21:19:47Z)
• Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense [27.471096446155933]
  We investigate the Post-Purification Robustness of current backdoor purification methods. We find that current safety purification methods are vulnerable to the rapid re-learning of backdoor behavior. We propose a tuning defense, Path-Aware Minimization (PAM), which promotes deviation along backdoor-connected paths with extra model updates.
  arXiv  Detail & Related papers  (2024-10-13T13:37:36Z)
• PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning [4.337364406035291]
  Backdoor attacks pose a significant threat to deep neural networks. We propose a novel mechanism, PAD-FT, that does not require an additional clean dataset and fine-tunes only a very small part of the model to disinfect the victim model. Our mechanism demonstrates superior effectiveness across multiple backdoor attack methods and datasets.
  arXiv  Detail & Related papers  (2024-09-18T15:47:23Z)
• Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models [3.134071086568745]
  Diffusion models (DMs) are regarded as one of the most advanced generative models today. Recent studies suggest that DMs are vulnerable to backdoor attacks. This vulnerability poses substantial risks, including reputational damage to model owners. We introduce Diff-Cleanse, a novel two-stage backdoor defense framework specifically designed for DMs.
  arXiv  Detail & Related papers  (2024-07-31T03:54:41Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Model X-ray:Detecting Backdoored Models via Decision Boundary [62.675297418960355]
  Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs) We propose Model X-ray, a novel backdoor detection approach based on the analysis of illustrated two-dimensional (2D) decision boundaries. Our approach includes two strategies focused on the decision areas dominated by clean samples and the concentration of label distribution.
  arXiv  Detail & Related papers  (2024-02-27T12:42:07Z)
• Can We Trust the Unlabeled Target Data? Towards Backdoor Attack and Defense on Model Adaptation [120.42853706967188]
  We explore the potential backdoor attacks on model adaptation launched by well-designed poisoning target data. We propose a plug-and-play method named MixAdapt, combining it with existing adaptation algorithms.
  arXiv  Detail & Related papers  (2024-01-11T16:42:10Z)
• Progressive Poisoned Data Isolation for Training-time Backdoor Defense [23.955347169187917]
  Deep Neural Networks (DNN) are susceptible to backdoor attacks where malicious attackers manipulate the model's predictions via data poisoning. In this study, we present a novel and efficacious defense method, termed Progressive Isolation of Poisoned Data (PIPD) Our PIPD achieves an average True Positive Rate (TPR) of 99.95% and an average False Positive Rate (FPR) of 0.06% for diverse attacks over CIFAR-10 dataset.
  arXiv  Detail & Related papers  (2023-12-20T02:40:28Z)
• Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective [71.39995120597999]
  Modern machine learning models are vulnerable to adversarial and backdoor attacks. Such risks are heightened by the prevalent practice of collecting massive, internet-sourced datasets for training multimodal models. CleanCLIP is the current state-of-the-art approach to mitigate the effects of backdooring in multimodal models.
  arXiv  Detail & Related papers  (2023-11-25T06:55:13Z)
• Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots [68.84056762301329]
  Recent research has exposed the susceptibility of pretrained language models (PLMs) to backdoor attacks. We propose and integrate a honeypot module into the original PLM to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features.
  arXiv  Detail & Related papers  (2023-10-28T08:21:16Z)
• Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples [67.66153875643964]
  Backdoor attacks are serious security threats to machine learning models. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk.
  arXiv  Detail & Related papers  (2023-07-20T03:56:04Z)
• 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)
• Backdoor Defense via Deconfounded Representation Learning [17.28760299048368]
  We propose a Causality-inspired Backdoor Defense (CBD) to learn deconfounded representations for reliable classification. CBD is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples.
  arXiv  Detail & Related papers  (2023-03-13T02:25:59Z)
• Mitigating Backdoors in Federated Learning with FLD [7.908496863030483]
  Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature has recently been found responsible for federated learning's vulnerability in the face of backdoor attacks. We propose Federated Layer Detection (FLD), a novel model filtering approach for effectively defending against backdoor attacks.
  arXiv  Detail & Related papers  (2023-03-01T07:54:54Z)

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.