CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models

• URL: http://arxiv.org/abs/2603.13435v1
• Date: Fri, 13 Mar 2026 08:05:50 GMT
• Title: CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models
• Abstract summary: We analyze the vulnerability of I2V models, find that temporal control mechanisms constitute a new attack surface, and reveal the challenge of modeling them uniformly.<n>We propose a trajectory-control attack, called CtrlAttack, to interfere with state evolution during the generation process.<n> Experimental results show that even under low-dimensional and strongly regularized perturbation constraints, our method can still significantly disrupt temporal consistency.
• Score: 92.04182855442254
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Diffusion-based image-to-video (I2V) models increasingly exhibit world-model-like properties by implicitly capturing temporal dynamics. However, existing studies have mainly focused on visual quality and controllability, and the robustness of the state transition learned by the model remains understudied. To fill this gap, we are the first to analyze the vulnerability of I2V models, find that temporal control mechanisms constitute a new attack surface, and reveal the challenge of modeling them uniformly under different attack settings. Based on this, we propose a trajectory-control attack, called CtrlAttack, to interfere with state evolution during the generation process. Specifically, we represent the perturbation as a low-dimensional velocity field and construct a continuous displacement field via temporal integration, thereby affecting the model's state transitions while maintaining temporal consistency; meanwhile, we map the perturbation to the observation space, making the method applicable to both white-box and black-box attack settings. Experimental results show that even under low-dimensional and strongly regularized perturbation constraints, our method can still significantly disrupt temporal consistency by increasing the attack success rate (ASR) to over 90% in the white-box setting and over 80% in the black-box setting, while keeping the variation of the FID and FVD within 6 and 130, respectively, thus revealing the potential security risk of I2V models at the level of state dynamics.

Related papers

• DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer [86.4618122245946]
  DyG$2$T is a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations.<n>Experiments on both synthetic and real-world datasets demonstrate that DyG$2$T achieves accurate dynamics modeling and reasoning.
  arXiv  Detail & Related papers  (2026-08-19T03:44:28Z)
• Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models [0.0]
  Hamiltonian Generative Networks (HGN) offer a principled path forward.<n>We show that HGN rollouts at step sizes beyond the training regime fail due to distinct failure modes.<n>In a detailed analysis, we recommend several strategies for enabling temporal generalization in continuous-time video generation.
  arXiv  Detail & Related papers  (2026-07-08T15:31:53Z)
• When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models [54.08784776767683]
  We present Physical-Conditioned World Model Attack (PhysCond-WMA), the first white-box world model attack that perturbs physical-condition channels.<n>PhysCond-WMA induces semantic, logic, or decision-level distortion while preserving perceptual fidelity.
  arXiv  Detail & Related papers  (2026-02-21T07:22:37Z)
• Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics [51.85385061275941]
  Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics.<n>Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation.<n>We present STAR-MD, a scalable diffusion model that generates physically plausible protein trajectories over micro-scale timescales.
  arXiv  Detail & Related papers  (2026-02-02T14:13:28Z)
• RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion [64.49056527678606]
  We propose a Token-wise Attention integrated into not only the U-Net diffusion model but also the radar-temporal encoder.<n>Unlike prior approaches, our method integrates attention into the architecture without incurring the high resource cost typical of pixel-space diffusion.<n>Our experiments and evaluations demonstrate that the proposed method significantly outperforms state-of-the-art approaches, robustness local fidelity, generalization, and superior in complex precipitation forecasting scenarios.
  arXiv  Detail & Related papers  (2025-10-16T17:59:13Z)
• Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection [43.49146665908238]
  Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision.<n>We introduce a novel frequency-guided diffusion model with perturbation training.<n>We employ the 2D Discrete Cosine Transform (DCT) to separate high-frequency (local) and low-frequency (global) motion components.
  arXiv  Detail & Related papers  (2024-12-04T05:43:53Z)
• Enhancing Adversarial Transferability with Adversarial Weight Tuning [50.01825144613307]
  adversarial examples (AEs) mislead the model while appearing benign to human observers.<n>AWT is a data-free tuning method that combines gradient-based and model-based attack methods to enhance the transferability of AEs.
  arXiv  Detail & Related papers  (2024-08-18T13:31:26Z)
• Real-Time Anomaly Detection and Reactive Planning with Large Language Models [18.57162998677491]
  Foundation models, e.g., large language models (LLMs), trained on internet-scale data possess zero-shot capabilities. We present a two-stage reasoning framework that incorporates the judgement regarding potential anomalies into a safe control framework. This enables our monitor to improve the trustworthiness of dynamic robotic systems, such as quadrotors or autonomous vehicles.
  arXiv  Detail & Related papers  (2024-07-11T17:59:22Z)

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.