Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning

• URL: http://arxiv.org/abs/2606.14078v1
• Date: Fri, 12 Jun 2026 03:55:04 GMT
• Title: Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning
• Abstract summary: Current backdoor defenses exhibit limited robustness and often fail against specific types of attacks.<n>We present a novel formulation of backdoor learning and unlearning as a sequential, three-stage process from a continual learning perspective.<n>Our method exhibits general applicability across a wide spectrum of backdoor attacks and can effectively and thoroughly eliminate the backdoor effects from a backdoor model.
• Score: 7.959552018607674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks. More concerningly, prevailing safety tuning strategies tend to provide only superficial safety protection, as they fall short of completely eliminating the backdoor effects. In this work, we present a novel formulation of backdoor learning and unlearning as a sequential, three-stage process from a continual learning perspective. Within this framework, we formally define complete backdoor unlearning and further derive the necessary conditions for achieving it based on the mechanism of catastrophic forgetting. Guided by these insights, we propose Blind Inversion-Backdoor Adversarial Unlearning (BI-BAU), which formulates the generation of adversarial examples satisfying the unlearning conditions as a blind inversion problem. We solve this by integrating the bi-level optimization process of adversarial training into an Expectation-Maximization (EM) algorithm framework to optimize the maximum a posteriori (MAP) objective. Furthermore, BI-BAU is extended to untargeted adversarial scenarios with unknown target classes, as well as to multi-modal contrastive learning tasks, enhancing its applicability to real-world deployment scenarios where pre-trained models may be compromised. Extensive experiments demonstrate that our method exhibits general applicability across a wide spectrum of backdoor attacks and can effectively and thoroughly eliminate the backdoor effects from a backdoor model.

Related papers

• BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning [34.532044428912144]
  Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy.<n>Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored.<n>We propose BadBone, a stealthy and adaptive backdoor attack against prompt learning using bi-level optimization.
  arXiv  Detail & Related papers  (2026-05-29T12:46:15Z)
• Backdoor Unlearning by Linear Task Decomposition [69.91984435094157]
  Foundation models are highly susceptible to adversarial perturbations and targeted backdoor attacks.<n>Existing backdoor removal approaches rely on costly fine-tuning to override the harmful behavior.<n>This raises the question of whether backdoors can be removed without compromising the general capabilities of the models.
  arXiv  Detail & Related papers  (2025-10-16T16:18:07Z)
• Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning [2.1896295740048894]
  We introduce the first paradigm of revocable backdoor attacks, where the backdoor can be proactively and thoroughly removed after the attack objective is achieved.<n>This work opens a new direction for backdoor attack research and presents new challenges for the security of machine learning systems.
  arXiv  Detail & Related papers  (2025-10-15T09:09:43Z)
• ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks [61.06621533874629]
  In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs)<n>In this paper, we propose, for the first time, the dual-learning hypothesis, which posits that LLMs simultaneously learn both the task-relevant latent concepts and backdoor latent concepts.<n>Motivated by these findings, we propose ICLShield, a defense mechanism that dynamically adjusts the concept preference ratio.
  arXiv  Detail & Related papers  (2025-07-02T03:09:20Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Behavior Backdoor for Deep Learning Models [95.50787731231063]
  We take the first step towards behavioral backdoor'' attack, which is defined as a behavior-triggered backdoor model training procedure.<n>We propose the first pipeline of implementing behavior backdoor, i.e., the Quantification Backdoor (QB) attack.<n>Experiments have been conducted on different models, datasets, and tasks, demonstrating the effectiveness of this novel backdoor attack.
  arXiv  Detail & Related papers  (2024-12-02T10:54:02Z)
• GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning [1.9632700283749582]
  This paper introduces a novel defense mechanism against backdoor attacks in federated learning, named GANcrop. Experimental findings demonstrate that GANcrop effectively safeguards against backdoor attacks, particularly in non-IID scenarios.
  arXiv  Detail & Related papers  (2024-05-31T09:33:16Z)
• Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning [49.242828934501986]
  Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features. backdoor attacks subtly embed malicious behaviors within the model during training. We introduce an innovative token-based localized forgetting training regime.
  arXiv  Detail & Related papers  (2024-03-24T18:33:15Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)

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.