Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation

• URL: http://arxiv.org/abs/2508.18235v1
• Date: Wed, 20 Aug 2025 00:57:21 GMT
• Title: Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
• Authors: Ashwath Vaithinathan Aravindan, Abha Jha, Matthew Salaway, Atharva Sandeep Bhide, Duygu Nur Yaldiz,
• Abstract summary: Adversaries can inject imperceptible textual triggers into training data, causing models to generate manipulated outputs.<n>We propose Self-Knowledge Distillation with Cross-Attention Guidance (SKD-CAG) to erase associations between adversarial text triggers and poisoned outputs.<n>Our method achieves removal accuracy 100% for pixel backdoors and 93% for style-based attacks, without sacrificing robustness or image fidelity.
• Score: 3.54387829918311
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to generate manipulated outputs. Although text-based backdoor defenses in classification models are well-explored, generative models lack effective mitigation techniques against. We address this by selectively erasing the model's learned associations between adversarial text triggers and poisoned outputs, while preserving overall generation quality. Our approach, Self-Knowledge Distillation with Cross-Attention Guidance (SKD-CAG), uses knowledge distillation to guide the model in correcting responses to poisoned prompts while maintaining image quality by exploiting the fact that the backdoored model still produces clean outputs in the absence of triggers. Using the cross-attention mechanism, SKD-CAG neutralizes backdoor influences at the attention level, ensuring the targeted removal of adversarial effects. Extensive experiments show that our method outperforms existing approaches, achieving removal accuracy 100\% for pixel backdoors and 93\% for style-based attacks, without sacrificing robustness or image fidelity. Our findings highlight targeted unlearning as a promising defense to secure generative models. Code and model weights can be found at https://github.com/Mystic-Slice/Sealing-The-Backdoor .

Related papers

• 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)
• 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)
• Backdoor Defense in Diffusion Models via Spatial Attention Unlearning [0.0]
  Text-to-image diffusion models are increasingly vulnerable to backdoor attacks.<n>We propose Spatial Attention Unlearning (SAU), a novel technique for mitigating backdoor attacks in diffusion models.
  arXiv  Detail & Related papers  (2025-04-21T04:00:19Z)
• Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP [51.04452017089568]
  Class-wise Backdoor Prompt Tuning (CBPT) is an efficient and effective defense mechanism that operates on text prompts to indirectly purify CLIP.<n>CBPT significantly mitigates backdoor threats while preserving model utility.
  arXiv  Detail & Related papers  (2025-02-26T16:25:15Z)
• Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images [0.0]
  Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels.<n>We introduce a groundbreaking method to detect unseen backdoored images during both training and inference.<n>Our approach trains learnable text prompts to differentiate clean images from those with hidden backdoor triggers.
  arXiv  Detail & Related papers  (2024-12-11T19:54:14Z)
• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models [65.30406788716104]
  This work investigates the vulnerabilities of security-enhancing diffusion models. We demonstrate that these models are highly susceptible to DIFF2, a simple yet effective backdoor attack. Case studies show that DIFF2 can significantly reduce both post-purification and certified accuracy across benchmark datasets and models.
  arXiv  Detail & Related papers  (2024-06-14T02:39:43Z)
• 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)
• Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data [26.551317580666353]
  Backdoor attacks pose a serious security threat for training neural networks. We propose a novel approach that enables model training on potentially poisoned datasets by utilizing the power of recent diffusion models.
  arXiv  Detail & Related papers  (2023-10-10T07:25:06Z)
• BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models [54.19289900203071]
  The rise in popularity of text-to-image generative artificial intelligence has attracted widespread public interest. We demonstrate that this technology can be attacked to generate content that subtly manipulates its users. We propose a Backdoor Attack on text-to-image Generative Models (BAGM) Our attack is the first to target three popular text-to-image generative models across three stages of the generative process.
  arXiv  Detail & Related papers  (2023-07-31T08:34:24Z)
• 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)
• 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)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)

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.