Dynamic Watermarking and Action-Conditioned Latent Dynamics for Secure Vision-Based Controllers
cs.RO, cs.CR, cs.SY, eess.SY
Submitted: 2026-11-05
Updated: 2026-11-05
Comments: 8 pages, 3 figures, Submitted to ACC 2027 conference
License: http://creativecommons.org/licenses/by/4.0/
The gist: Replay attacks are difficult to detect in vision-based control systems because previously recorded observations can remain plausible while the physical system follows a different trajectory.
Terminology
Abstract
Replay attacks are difficult to detect in vision-based control systems because previously recorded observations can remain plausible while the physical system follows a different trajectory. This paper develops an adaptive dynamic-watermarking framework for detecting replay attacks against vision-based controllers. A private Gaussian watermark is added to the nominal control input, and a control input-conditioned latent dynamics network (LDN) predicts the corresponding evolution in a compact latent space learned from image observations. Attack evidence is obtained from the discrepancy between the predicted latent response and the latent representation of the received image observation. A reinforcement learning policy adjusts the watermark covariance using the latent state and detector confidence, thereby balancing attack detectability, watermark energy, and control distortion. A Lagrangian penalty on task-specific safety costs is included during training to limit the adverse effect of the excitation. The framework is evaluated on a vision-guided UR5 manipulation task in which the robot reaches a target while avoiding a moving human arm under nominal and replay-attacked observations.
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Proximal Policy Optimization Algorithms
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation