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

arXiv: https://arxiv.org/abs/2509.12824 · HTML: https://mlsanity.com/paper/2509.12824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability](https://mlsanity.com/paper/2305.16494/) (2023)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Targeted Attack for Deep Hashing based Retrieval](https://mlsanity.com/paper/2004.07955/) (2020)
- [DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection](https://mlsanity.com/paper/2405.09882/) (2024)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing](https://mlsanity.com/paper/2105.07553/) (2021)
- [AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks](https://mlsanity.com/paper/2503.09124/) (2025)
- [SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion](https://mlsanity.com/paper/2311.12981/) (2023)
- [Deep Priority Hashing](https://mlsanity.com/paper/1809.01238/) (2018)
- [CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval](https://mlsanity.com/paper/2204.10779/) (2022)

## Abstract (arXiv)

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.