DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings

• URL: http://arxiv.org/abs/2606.22779v1
• Date: Mon, 22 Jun 2026 02:42:38 GMT
• Title: DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings
• Abstract summary: We introduce DE-FIVE, a training-free framework for detecting malicious image prompts.<n>We develop a hybrid detection strategy consisting of a black-box detector and a white-box detector.<n>Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art baselines against malicious image prompts.
• Score: 0.870967746482596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision language models (VLMs) employ both visual and textual modalities to enable advanced vision-language inference. However, incorporating visual modalities expands the attack surface of VLMs, making them more susceptible to security threats such as adversarial perturbations and indirect prompt injection, wherein crafted malicious image prompts can elicit unintended model outputs. Existing defense methods against malicious image prompts remain insufficient as they typically demand extensive datasets for retraining or the deployment of additional, complex classifiers. Most critically, there is a profound lack of specialized defense mechanisms specifically targeting indirect prompt injections, a gap that serves as a primary motivation for this work. To address these limitations, we introduce DE-FIVE, a novel training-free framework for detecting malicious image prompts by leveraging Fourier features and the hidden state representations of the visual encoder (image vector embeddings) across perturbations. Specifically, we develop a hybrid detection strategy consisting of a black-box detector that operates on Fourier-domain features and a white-box detector that exploits image vector embeddings derived from only a few-shot malicious set. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art baselines against malicious image prompts.

Related papers

• Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing [59.765442274924595]
  We propose a compositional visual prompt learning framework that operates entirely in the visual feature space.<n>The framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units.<n>Experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.
  arXiv  Detail & Related papers  (2026-08-18T04:18:08Z)
• TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors [76.4118981404995]
  Trajectory-Injected Generative Attack (TIGA) is a source-image-free and training free framework that generates detector-evasive images.<n>TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation.<n>TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations.
  arXiv  Detail & Related papers  (2026-07-28T15:51:39Z)
• Towards Robustness against Typographic Attack with Training-free Concept Localization [42.575178574443946]
  Contrastive Language-Image Pretraining models (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs)<n>CLIP models exhibit a critical yet underexplored failure mode: irrelevant text appearing within images confounds visual representations, biasing them toward lexical meaning rather than true visual semantics.<n>This issue, commonly described as a Typographic Attack (TA), exposes a vulnerability that poses a significant risk to safety-critical applications such as autonomous driving.<n>We propose a novel, training-free mechanistic interpretability method to achieve interpretable and effective robustness against TA.
  arXiv  Detail & Related papers  (2026-07-02T17:55:24Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents [21.863110073132773]
  Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation.<n>They inherently expand the attack surface, introducing novel vision-based vulnerabilities.<n>We propose MIRAGE, a novel visual indirect prompt injection framework for targeted next-action hijacking.
  arXiv  Detail & Related papers  (2026-06-16T15:31:33Z)
• Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection [58.927873049646024]
  We show that fake images cannot be properly aligned with corresponding captions compared to real images.<n>We propose a simple yet effective ITEM by leveraging the image-text misalignment in a joint visual-language space as discriminative clues.
  arXiv  Detail & Related papers  (2025-11-01T06:51:14Z)
• PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting [25.24109316946351]
  We propose PromptFlare, a novel adversarial protection method designed to protect images from malicious modifications facilitated by diffusion-based inpainting models.<n>Our approach exploits the intrinsic properties of prompt embeddings and injects adversarial noise to suppress the sampling process.<n>Experiments on the EditBench dataset demonstrate that our method achieves state-of-the-art performance across various metrics.
  arXiv  Detail & Related papers  (2025-08-22T08:42:46Z)
• ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack [56.0056378072843]
  We show that highly transferable adversarial images can be crafted solely via the upstream model.<n>We propose ForensicsSAM, a unified IFDL framework with built-in adversarial robustness.
  arXiv  Detail & Related papers  (2025-08-10T16:03:44Z)
• Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense [0.0]
  Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks.<n>In this paper, we introduce DBOM, a proactive framework that leverages structured disentanglement to identify and neutralize both seen and unseen backdoor threats.<n>We show that DBOM robustly detects poisoned images prior to downstream training, significantly enhancing the security of training pipelines.
  arXiv  Detail & Related papers  (2025-08-03T21:58:15Z)
• Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detection [71.60120616284246]
  We propose a novel knowledge-based prompt learning framework to explore the strong generalization capability of vision-language models for 3D mask presentation attack detection.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art intra- and cross-scenario detection performance.
  arXiv  Detail & Related papers  (2025-05-06T15:09:23Z)
• ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization [49.12958154544838]
  ForgeryGPT is a novel framework that advances the Image Forgery Detection and localization task.<n>It captures high-order correlations of forged images from diverse linguistic feature spaces.<n>It enables explainable generation and interactive dialogue through a newly customized Large Language Model (LLM) architecture.
  arXiv  Detail & Related papers  (2024-10-14T07:56:51Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)

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.