Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing

• URL: http://arxiv.org/abs/2509.23279v1
• Date: Sat, 27 Sep 2025 12:26:34 GMT
• Title: Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
• Authors: Rohit Chowdhury, Aniruddha Bala, Rohan Jaiswal, Siddharth Roheda,
• Abstract summary: We introduce Vid-Freeze - a novel attention-suppressing adversarial attack that adds carefully crafted adversarial perturbations to images.<n>Our method explicitly targets the attention mechanism of I2V models, completely disrupting motion synthesis.<n>The resulting immunized images generate stand-still or near-static videos, effectively blocking malicious content creation.
• Score: 2.48490797934472
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid progress of image-to-video (I2V) generation models has introduced significant risks, enabling video synthesis from static images and facilitating deceptive or malicious content creation. While prior defenses such as I2VGuard attempt to immunize images, effective and principled protection to block motion remains underexplored. In this work, we introduce Vid-Freeze - a novel attention-suppressing adversarial attack that adds carefully crafted adversarial perturbations to images. Our method explicitly targets the attention mechanism of I2V models, completely disrupting motion synthesis while preserving semantic fidelity of the input image. The resulting immunized images generate stand-still or near-static videos, effectively blocking malicious content creation. Our experiments demonstrate the impressive protection provided by the proposed approach, highlighting the importance of attention attacks as a promising direction for robust and proactive defenses against misuse of I2V generation models.

Related papers

• VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models [57.128876964730644]
  Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability.<n>We propose Visual Instruction Injection (VII), a training-free and transferable jailbreaking framework that disguises the malicious intent of unsafe text prompts as benign visual instructions in the safe reference image.<n>VII achieves Attack Success Rates of up to 83.5% while reducing Refusal Rates to near zero, significantly outperforming existing baselines.
  arXiv  Detail & Related papers  (2026-02-24T15:20:01Z)
• Towards Transferable Defense Against Malicious Image Edits [70.17363183107604]
  Transferable Defense Against Malicious Image Edits (TDAE) is a novel bimodal framework that enhances image immunity against malicious edits.<n>We introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective.<n>For textual enhancement protection, we propose Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images.
  arXiv  Detail & Related papers  (2025-12-16T12:10:16Z)
• DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models [74.9510349783152]
  Malicious actors can exploit diffusion model customization with just a few or even one image of a person to create synthetic identities nearly identical to the original identity.<n>This paper proposes Dual-Layer Anti-Diffusion (DLADiff) to defend both fine-tuning methods and zero-shot methods.
  arXiv  Detail & Related papers  (2025-11-25T04:35:55Z)
• Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation [26.890796322896346]
  Defense mechanisms like Anti-DreamBooth attempt to mitigate the risk of facial identity leakage.<n>We identify two critical yet overlooked limitations of these methods.<n>Results reveal that none of the current methods maintains their protective effectiveness under such threats.
  arXiv  Detail & Related papers  (2025-11-13T14:56:25Z)
• VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation [57.36681904639463]
  Methods to safeguard autoregressive text-to-image models remain underexplored.<n>We propose Visual Contrast Exploitation (VCE), a novel framework that precisely decouples unsafe concepts from their associated content semantics.<n>Our experiments demonstrate that our method effectively secures the model, achieving state-of-the-art results while erasing unsafe concepts and maintaining the integrity of unrelated safe concepts.
  arXiv  Detail & Related papers  (2025-09-21T09:00:27Z)
• BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation [37.055665794706336]
  Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing.<n>We observe that in T2V generation tasks, the generated videos often contain substantial redundant information not explicitly specified in the text prompts.<n>We introduce BadVideo, the first backdoor attack framework tailored for T2V generation.
  arXiv  Detail & Related papers  (2025-04-23T17:34:48Z)
• Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense [90.71884758066042]
  Large vision-language models (LVLMs) introduce a unique vulnerability: susceptibility to malicious attacks via visual inputs.<n>We propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism.
  arXiv  Detail & Related papers  (2025-03-14T17:39:45Z)
• AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models [33.29825481203704]
  AdvI2I is a novel framework that manipulates input images to induce diffusion models to generate NSFW content.<n>By optimizing a generator to craft adversarial images, AdvI2I circumvents existing defense mechanisms.<n>We show that both AdvI2I and AdvI2I-Adaptive can effectively bypass current safeguards.
  arXiv  Detail & Related papers  (2024-10-28T19:15:06Z)
• Adversarial Prompt Tuning for Vision-Language Models [86.5543597406173]
  Adversarial Prompt Tuning (AdvPT) is a technique to enhance the adversarial robustness of image encoders in Vision-Language Models (VLMs) We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques.
  arXiv  Detail & Related papers  (2023-11-19T07:47:43Z)
• DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection [64.77548539959501]
  DiffProtect produces more natural-looking encrypted images than state-of-the-art methods. It achieves significantly higher attack success rates, e.g., 24.5% and 25.1% absolute improvements on the CelebA-HQ and FFHQ datasets.
  arXiv  Detail & Related papers  (2023-05-23T02:45:49Z)
• Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework [20.652130361862053]
  We propose the Adversarial Decoupling Augmentation Framework (ADAF) to enhance the defensive performance of facial privacy protection algorithms. ADAF introduces multi-level text-related augmentations for defense stability against various attacker prompts.
  arXiv  Detail & Related papers  (2023-05-06T09:00:50Z)
• Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks [67.58887471137436]
  We develop a novel defense method using temporal shuffling of input videos against adversarial attacks for action recognition models. To the best of our knowledge, this is the first attempt to design a defense method without additional training for 3D CNN-based video action recognition models.
  arXiv  Detail & Related papers  (2021-12-15T06:57:01Z)

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.