Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling

• URL: http://arxiv.org/abs/2604.12446v1
• Date: Tue, 14 Apr 2026 08:31:37 GMT
• Title: Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
• Abstract summary: Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks.<n>Existing defenses, particularly input-level methods, are more practical for deployment but often rely on observable anomalies that become unreliable under stealthy, semantics-preserving trigger designs.<n>We propose SET, an input-level backdoor detection framework that constructs response-offset features under multi-scale perturbations and learns a compact benign response space from a small set of clean samples.
• Score: 12.573852448122716
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level methods, are more practical for deployment but often rely on observable anomalies that become unreliable under stealthy, semantics-preserving trigger designs. As modern backdoor attacks increasingly embed triggers into natural inputs, these methods degrade substantially, raising a critical question: can more stable, implicit, and trigger-agnostic differences between benign and backdoor inputs be exploited for detection? In this work, we address this challenge from an active probing perspective. We introduce controlled scaling perturbations on cross-attention and uncover a novel phenomenon termed Cross-Attention Scaling Response Divergence (CSRD), where benign and backdoor inputs exhibit systematically different response evolution patterns across denoising steps. Building on this insight, we propose SET, an input-level backdoor detection framework that constructs response-offset features under multi-scale perturbations and learns a compact benign response space from a small set of clean samples. Detection is then performed by measuring deviations from this learned space, without requiring prior knowledge of the attack or access to model training. Extensive experiments demonstrate that SET consistently outperforms existing baselines across diverse attack methods, trigger types, and model settings, with particularly strong gains under stealthy implicit-trigger scenarios. Overall, SET improves AUROC by 9.1% and ACC by 6.5% over the best baseline, highlighting its effectiveness and robustness for practical deployment.

Related papers

• STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling [31.05830693695975]
  We propose STEP (Stability-based Trigger Exposure Profiling), a black-box, retraining-free backdoor detector that operates under hard-label-only access.<n>Its core idea is to exploit a characteristic dual anomaly of backdoor triggers: anomalous label stability under semantic-breaking perturbations, and anomalous label fragility under semantic-preserving perturbations.<n>Experiments show that STEP achieves an average AUROC of 97.92% and EER of 4.54%, substantially outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-18T12:14:14Z)
• 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)
• Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift [23.0914017433021]
  This work identifies a novel class of deployment phase attacks that exploit a vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text.<n>We propose Search based Embedding Poisoning, a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens.
  arXiv  Detail & Related papers  (2025-09-08T05:00:58Z)
• DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion [0.7351161122478707]
  Deep neural networks are vulnerable to Trojan (backdoor) attacks.<n> triggerAdaptive inversion reconstructs malicious "shortcut" patterns inserted by an adversary during training.<n>We propose a data-free, zero-shot trigger-inversion strategy that restricts the search space while avoiding strong assumptions on trigger appearance.
  arXiv  Detail & Related papers  (2025-07-30T16:31:13Z)
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers [0.0]
  Large language models (LLMs) aligned for safety often exhibit emergent deceptive behaviors.<n>This paper introduces adversarial activation patching, a novel mechanistic interpretability framework.<n>By sourcing activations from "deceptive" prompts, we simulate vulnerabilities and quantify deception rates.
  arXiv  Detail & Related papers  (2025-07-12T21:29:49Z)
• Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models [70.03122709795122]
  Previous backdoor detection methods primarily focus on the static features of backdoor samples.<n>This study introduces a novel backdoor detection perspective named Dynamic Attention Analysis (DAA), showing that these dynamic characteristics serve as better indicators for backdoor detection.<n>Our approach significantly surpasses existing detection methods, achieving an average F1 Score of 79.49% and an AUC of 87.67%.
  arXiv  Detail & Related papers  (2025-04-29T07:59:35Z)
• Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models [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 Trigger without Trace (TwT) by explicitly mitigating these consistencies.
  arXiv  Detail & Related papers  (2025-03-22T10:41:46Z)
• 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)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [81.93945602120453]
  We introduce an approach that is both general and parameter-efficient for face forgery detection.<n>We design a forgery-style mixture formulation that augments the diversity of forgery source domains.<n>We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• 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)

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.