BURN: Backdoor Unlearning via Adversarial Boundary Analysis

• URL: http://arxiv.org/abs/2507.10491v1
• Date: Mon, 14 Jul 2025 17:13:06 GMT
• Title: BURN: Backdoor Unlearning via Adversarial Boundary Analysis
• Authors: Yanghao Su, Jie Zhang, Yiming Li, Tianwei Zhang, Qing Guo, Weiming Zhang, Nenghai Yu, Nils Lukas, Wenbo Zhou,
• Abstract summary: 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.
• Score: 73.14147934175604
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic labels of poison samples. This limitation prevents them from fully eliminating the false correlation between the trigger pattern and the target label. To address this, we leverage boundary adversarial attack techniques, revealing two key observations. First, poison samples exhibit significantly greater distances from decision boundaries compared to clean samples, indicating they require larger adversarial perturbations to change their predictions. Second, while adversarial predicted labels for clean samples are uniformly distributed, those for poison samples tend to revert to their original correct labels. Moreover, the features of poison samples restore to closely resemble those of corresponding clean samples after adding adversarial perturbations. Building upon these insights, we propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification. In the first phase, BURN employs adversarial boundary analysis to detect poisoned samples based on their abnormal adversarial boundary distances, then restores their correct semantic labels for fine-tuning. In the second phase, it employs a feedback mechanism that tracks prediction discrepancies between the original backdoored model and progressively sanitized models, guiding both dataset refinement and model purification. Extensive evaluations across multiple datasets, architectures, and seven diverse backdoor attack types confirm that BURN effectively removes backdoor threats while maintaining the model's original performance.

Related papers

• Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models [12.519879298717104]
  We propose a stealthy backdoor sample detection method based on Reference-Filtration and Tfidf-Clustering mechanisms.<n>Experiments on two machine translation datasets and one QA dataset demonstrate that RFTC outperforms baselines in backdoor detection and model performance.
  arXiv  Detail & Related papers  (2025-05-29T02:49:29Z)
• Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model [70.03122709795122]
  Backdoor attacks targeting text-to-image diffusion models have advanced rapidly.<n>Current backdoor samples often exhibit two key abnormalities compared to benign samples.<n>We propose a novel Invisible Backdoor Attack (IBA) to enhance the stealthiness of backdoor samples.
  arXiv  Detail & Related papers  (2025-03-22T10:41:46Z)
• Detecting Backdoor Attacks via Similarity in Semantic Communication Systems [3.565151496245487]
  This work proposes a defense mechanism that leverages semantic similarity to detect backdoor attacks.<n>By analyzing deviations in semantic feature space and establishing a threshold-based detection framework, the proposed approach effectively identifies poisoned samples.
  arXiv  Detail & Related papers  (2025-02-06T02:22:36Z)
• PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection [57.571451139201855]
  Prediction Shift Backdoor Detection (PSBD) is a novel method for identifying backdoor samples in deep neural networks.<n>PSBD is motivated by an intriguing Prediction Shift (PS) phenomenon, where poisoned models' predictions on clean data often shift away from true labels towards certain other labels.<n>PSBD identifies backdoor training samples by computing the Prediction Shift Uncertainty (PSU), the variance in probability values when dropout layers are toggled on and off during model inference.
  arXiv  Detail & Related papers  (2024-06-09T15:31:00Z)
• 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)
• ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP [29.375957205348115]
  We propose an innovative test-time poisoned sample detection framework that hinges on the interpretability of model predictions. We employ ChatGPT, a state-of-the-art large language model, as our paraphraser and formulate the trigger-removal task as a prompt engineering problem.
  arXiv  Detail & Related papers  (2023-08-04T03:48:28Z)
• 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)
• Exploring Model Dynamics for Accumulative Poisoning Discovery [62.08553134316483]
  We propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information. By implicitly transferring the changes in the data manipulation to that in the model outputs, Memorization Discrepancy can discover the imperceptible poison samples. We thoroughly explore its properties and propose Discrepancy-aware Sample Correction (DSC) to defend against accumulative poisoning attacks.
  arXiv  Detail & Related papers  (2023-06-06T14:45:24Z)
• Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency [33.42013309686333]
  We propose a test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Extensive experiments demonstrate that compared with state-of-the-art defenses, TeCo outperforms them on different backdoor attacks, datasets, and model architectures.
  arXiv  Detail & Related papers  (2023-03-27T07:10:37Z)
• 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)
• A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks [72.7373468905418]
  We develop an open-source toolkit OpenBackdoor to foster the implementations and evaluations of textual backdoor learning. We also propose CUBE, a simple yet strong clustering-based defense baseline.
  arXiv  Detail & Related papers  (2022-06-17T02:29:23Z)

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.