A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement

• URL: http://arxiv.org/abs/2506.23676v1
• Date: Mon, 30 Jun 2025 09:59:09 GMT
• Title: A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement
• Authors: Gaozheng Pei, Ke Ma, Dongpeng Zhang, Chengzhi Sun, Qianqian Xu, Qingming Huang,
• Abstract summary: We propose a unified framework that seamlessly incorporates traditional transferability enhancement strategies into diffusion model-based adversarial example generation via image editing.<n>Our method won first place in the "1st Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Media" competition at ACM MM25.
• Score: 72.3054292908678
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion model, these diffusion-based methods often struggle to generalize beyond conventional image classification tasks, such as in Deepfake detection. Moreover, traditional strategies for enhancing adversarial example transferability are challenging to adapt to these methods. To address these challenges, we propose a unified framework that seamlessly incorporates traditional transferability enhancement strategies into diffusion model-based adversarial example generation via image editing, enabling their application across a wider range of downstream tasks. Our method won first place in the "1st Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Media" competition at ACM MM25, which validates the effectiveness of our approach.

Related papers

• EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM [50.054404519821745]
  We present a novel framework that integrates a multimodal Large Language Model for enhanced reasoning capabilities.<n>Our framework achieves promising results on MagicBrush, AutoSplice, and PerfBrush datasets.<n> Notably, our method excels on the PerfBrush dataset, a self-constructed test set featuring previously unseen types of edits.
  arXiv  Detail & Related papers  (2024-12-05T02:05:33Z)
• Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models [32.23201683108716]
  We propose a novel strategy that exclusively employs image patches for attacks, thus preserving the integrity of the original text. Our method leverages prior knowledge from diffusion models to enhance the authenticity and naturalness of the perturbations. Comprehensive experiments conducted in a white-box setting for image-to-text scenarios reveal that our proposed method significantly outperforms existing techniques, achieving a 100% attack success rate.
  arXiv  Detail & Related papers  (2024-10-07T10:06:01Z)
• Pixel Is Not a Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models [9.905296922309157]
  Diffusion Models have emerged as powerful generative models for high-quality image synthesis, with many subsequent image editing techniques based on them.<n>Previous works have attempted to safeguard images from diffusion-based editing by adding imperceptible perturbations.<n>Our work proposes a novel attack framework, AtkPDM, which exploits vulnerabilities in denoising UNets and a latent optimization strategy to enhance the naturalness of adversarial images.
  arXiv  Detail & Related papers  (2024-08-21T17:56:34Z)
• JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits [76.25962336540226]
  JIGMARK is a first-of-its-kind watermarking technique that enhances robustness through contrastive learning. Our evaluation reveals that JIGMARK significantly surpasses existing watermarking solutions in resilience to diffusion-model edits.
  arXiv  Detail & Related papers  (2024-06-06T03:31:41Z)
• Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models [11.91784429717735]
  We propose CAAT, a generic and efficient approach to fool latent diffusion models (LDMs) We show that a subtle gradient on an image can significantly impact the cross-attention layers, thus changing the mapping between text and image. Experiments demonstrate that CAAT is compatible with diverse diffusion models and outperforms baseline attack methods.
  arXiv  Detail & Related papers  (2024-04-23T14:31:15Z)
• GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models [4.710921988115686]
  We introduce GANTASTIC, a novel framework that takes existing directions from pre-trained GAN models and transfers these directions into diffusion-based models. This approach not only maintains the generative quality and diversity that diffusion models are known for but also significantly enhances their capability to perform precise, targeted image edits.
  arXiv  Detail & Related papers  (2024-03-28T17:55:16Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• 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)
• DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing [94.24479528298252]
  DragGAN is an interactive point-based image editing framework that achieves impressive editing results with pixel-level precision. By harnessing large-scale pretrained diffusion models, we greatly enhance the applicability of interactive point-based editing on both real and diffusion-generated images. We present a challenging benchmark dataset called DragBench to evaluate the performance of interactive point-based image editing methods.
  arXiv  Detail & Related papers  (2023-06-26T06:04:09Z)
• Enhancing the Self-Universality for Transferable Targeted Attacks [88.6081640779354]
  Our new attack method is proposed based on the observation that highly universal adversarial perturbations tend to be more transferable for targeted attacks. Instead of optimizing the perturbations on different images, optimizing on different regions to achieve self-universality can get rid of using extra data. With the feature similarity loss, our method makes the features from adversarial perturbations to be more dominant than that of benign images.
  arXiv  Detail & Related papers  (2022-09-08T11:21:26Z)
• Random Transformation of Image Brightness for Adversarial Attack [5.405413975396116]
  adversarial examples are crafted by adding small, human-imperceptibles to the original images. Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptibles to the original images. We propose an adversarial example generation method based on this phenomenon, which can be integrated with Fast Gradient Sign Method. Our method has a higher success rate for black-box attacks than other attack methods based on data augmentation.
  arXiv  Detail & Related papers  (2021-01-12T07:00:04Z)

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.