DiffHash: Text-Guided Targeted Attack via Diffusion Models against Deep Hashing Image Retrieval

• URL: http://arxiv.org/abs/2509.12824v2
• Date: Wed, 17 Sep 2025 07:49:58 GMT
• Title: DiffHash: Text-Guided Targeted Attack via Diffusion Models against Deep Hashing Image Retrieval
• Authors: Zechao Liu, Zheng Zhou, Xiangkun Chen, Tao Liang, Dapeng Lang,
• Abstract summary: Deep hashing models have been widely adopted to tackle the challenges of large-scale image retrieval.<n>Deep hashing models face serious security risks due to their vulnerability to adversarial examples.<n>We propose DiffHash, a novel diffusion-based targeted attack for deep hashing.
• Score: 8.42949283173691
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep hashing models have been widely adopted to tackle the challenges of large-scale image retrieval. However, these approaches face serious security risks due to their vulnerability to adversarial examples. Despite the increasing exploration of targeted attacks on deep hashing models, existing approaches still suffer from a lack of multimodal guidance, reliance on labeling information and dependence on pixel-level operations for attacks. To address these limitations, we proposed DiffHash, a novel diffusion-based targeted attack for deep hashing. Unlike traditional pixel-based attacks that directly modify specific pixels and lack multimodal guidance, our approach focuses on optimizing the latent representations of images, guided by text information generated by a Large Language Model (LLM) for the target image. Furthermore, we designed a multi-space hash alignment network to align the high-dimension image space and text space to the low-dimension binary hash space. During reconstruction, we also incorporated text-guided attention mechanisms to refine adversarial examples, ensuring them aligned with the target semantics while maintaining visual plausibility. Extensive experiments have demonstrated that our method outperforms state-of-the-art (SOTA) targeted attack methods, achieving better black-box transferability and offering more excellent stability across datasets.

Related papers

• Model Inversion Attack Against Deep Hashing [0.9055220224305597]
  DHMI is the first diffusion-based model inversion framework designed for deep hashing.<n>It reconstructs high-resolution, high-quality images even under the most challenging black-box setting.<n>Our method outperforms the existing state-of-the-art model inversion attacks in black-box scenarios.
  arXiv  Detail & Related papers  (2025-11-15T14:21:16Z)
• Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings [1.104960878651584]
  Deep neural networks for image classification remain vulnerable to adversarial examples.<n>We propose Targeted Edge-informed Attack (TEA), a novel attack that utilizes edge information from the target image to carefully perturb it.<n>Our approach consistently outperforms current state-of-the-art methods across different models in low query settings.
  arXiv  Detail & Related papers  (2025-05-22T07:10:12Z)
• Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing [71.30876587855867]
  We show that even clean query images can be dangerous, inducing malicious target retrieval results, like undesired or illegal images.<n>Specifically, we first train a surrogate model to simulate the behavior of the target deep hashing model.<n>Then, a strict gradient matching strategy is proposed to generate the poisoned images.
  arXiv  Detail & Related papers  (2025-03-27T07:54:27Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model [61.53213964333474]
  We propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness.
  arXiv  Detail & Related papers  (2023-12-18T15:25:23Z)
• Semantic Adversarial Attacks via Diffusion Models [30.169827029761702]
  Semantic adversarial attacks focus on changing semantic attributes of clean examples, such as color, context, and features. We propose a framework to quickly generate a semantic adversarial attack by leveraging recent diffusion models. Our approaches achieve approximately 100% attack success rate in multiple settings with the best FID as 36.61.
  arXiv  Detail & Related papers  (2023-09-14T02:57:48Z)
• 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)
• Two-branch Multi-scale Deep Neural Network for Generalized Document Recapture Attack Detection [25.88454144842164]
  The image recapture attack is an effective image manipulation method to erase certain forensic traces, and when targeting on personal document images, it poses a great threat to the security of e-commerce and other web applications. We propose a novel two-branch deep neural network by mining better generalized recapture artifacts with a designed frequency filter bank and multi-scale cross-attention fusion module.
  arXiv  Detail & Related papers  (2022-11-30T06:57:11Z)
• Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing [65.32148145602865]
  deep hashing networks are vulnerable to adversarial examples. We propose a novel prototype-supervised adversarial network (ProS-GAN) To the best of our knowledge, this is the first generation-based method to attack deep hashing networks.
  arXiv  Detail & Related papers  (2021-05-17T00:31:37Z)
• Targeted Attack for Deep Hashing based Retrieval [57.582221494035856]
  We propose a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on such retrieval. We first formulate the targeted attack as a point-to-set optimization, which minimizes the average distance between the hash code of an adversarial example and those of a set of objects with the target label. To balance the performance and perceptibility, we propose to minimize the Hamming distance between the hash code of the adversarial example and the anchor code under the $ellinfty$ restriction on the perturbation.
  arXiv  Detail & Related papers  (2020-04-15T08:36:58Z)

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.