IP-Bench: Benchmark for Image Protection Methods in Image-to-Video Generation Scenarios

• URL: http://arxiv.org/abs/2603.26154v1
• Date: Fri, 27 Mar 2026 08:11:33 GMT
• Title: IP-Bench: Benchmark for Image Protection Methods in Image-to-Video Generation Scenarios
• Abstract summary: IP-Bench is the first systematic benchmark designed to evaluate image protection methods in I2V generation scenarios.<n>This benchmark examines 6 representative protection methods and 5 state-of-the-art I2V models.<n>Overall, IP-Bench establishes a systematic, reproducible, and evaluation framework for image protection methods in I2V generation scenarios.
• Score: 13.66248113146474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid advancement of image-to-video (I2V) generation models, their potential for misuse in creating malicious content has become a significant concern. For instance, a single image can be exploited to generate a fake video, which can be used to attract attention and gain benefits. This phenomenon is referred to as an I2V generation misuse. Existing image protection methods suffer from the absence of a unified benchmark, leading to an incomplete evaluation framework. Furthermore, these methods have not been systematically assessed in I2V generation scenarios and against preprocessing attacks, which complicates the evaluation of their effectiveness in real-world deployment scenarios.To address this challenge, we propose IP-Bench (Image Protection Bench), the first systematic benchmark designed to evaluate protection methods in I2V generation scenarios. This benchmark examines 6 representative protection methods and 5 state-of-the-art I2V models. Furthermore, our work systematically evaluates protection methods' robustness with two robustness attack strategies under practical scenarios and analyzes their cross-model & cross-modality transferability. Overall, IP-Bench establishes a systematic, reproducible, and extensible evaluation framework for image protection methods in I2V generation scenarios.

Related papers

• IP Protection in the Era of Visual Generative AI: A Survey [70.06761647752164]
  This survey presents a two-dimensional taxonomy for IP protection in visual generative models.<n>The primary axis is a Control Logic View, which classifies methods into Information Exposure Control, Generative Behavior Constraint, and Attribution & Accountability.<n>The secondary axis distinguishes Data IP from Model IP as cross-cutting asset dimensions.
  arXiv  Detail & Related papers  (2026-08-13T00:26:41Z)
• I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models [4.606986864282809]
  Video generation models have led to the increasing misuse of image-to-video (I2V) models.<n>Current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks.<n>We propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to I2V models.
  arXiv  Detail & Related papers  (2026-07-28T10:05:11Z)
• Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models [9.029672953412787]
  Text-to-Image generative models are vulnerable to adversarial misuse.<n>Most existing jailbreak attacks rely on prompt engineering or black-box optimization.<n>We propose MIND, a cognitive jailbreak framework that reframes adversarial prompt generation as a belief-state inference problem.
  arXiv  Detail & Related papers  (2026-07-20T10:09:30Z)
• Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation [10.54860936583801]
  Recent advances in I2V generation allow a single image to be animated into a convincing video under text guidance.<n>We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image.
  arXiv  Detail & Related papers  (2026-07-01T22:00:18Z)
• VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks [27.060981309996492]
  We present the first systematic benchmark for evaluating video generation safety under vision-centric prompt attacks.<n>We propose VPA-Guard, a retrieval-augmented and self-evolving defense framework.
  arXiv  Detail & Related papers  (2026-06-24T09:00:08Z)
• RunawayEvil: Jailbreaking the Image-to-Video Generative Models [59.21761412103083]
  Image-to-Video (I2V) generation synthesizes dynamic visual content from image and text inputs, providing significant creative control.<n>We propose RunawayEvil, the first multimodal jailbreak framework for I2V models with dynamic evolutionary capability.<n>We show RunawayEvil achieves state-of-the-art attack success rates on commercial I2V models, such as Open-Sora 2.0 and CogVideoX.
  arXiv  Detail & Related papers  (2025-12-07T06:14:52Z)
• ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection [27.47621607462884]
  ConceptGuard is a framework for proactively detecting and mitigating unsafe semantics in multimodal video generation.<n>A contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space.<n>A semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning.
  arXiv  Detail & Related papers  (2025-11-24T05:27:05Z)
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks [67.91652526657599]
  We formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail.<n>We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models.<n>The proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate.
  arXiv  Detail & Related papers  (2025-05-10T16:04:52Z)
• T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models [88.63040835652902]
  Text to video models are vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of harmful or unsafe content.<n>We propose T2VShield, a comprehensive and model agnostic defense framework designed to protect text to video models from jailbreak threats.<n>Our method systematically analyzes the input, model, and output stages to identify the limitations of existing defenses.
  arXiv  Detail & Related papers  (2025-04-22T01:18:42Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• 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)

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.