FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models

TL;DR

FlowHijack exposes a critical security vulnerability in flow-matching vision-language-action models by manipulating their vector field dynamics, enabling stealthy backdoor attacks without degrading normal performance.

Contribution

This paper introduces the first backdoor attack framework targeting the dynamics of flow-matching VLAs, combining a novel injection strategy with a regularizer to achieve high success and stealth.

Findings

FlowHijack achieves high attack success rates with stealthy triggers.

It preserves benign task performance while executing malicious actions.

Malicious actions are behaviorally indistinguishable from normal actions.

Abstract

Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $\pi_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation mechanism - the vector field dynamics - presents a critical yet unexplored security vulnerability, particularly backdoor vulnerabilities. Existing backdoor attacks designed for autoregressive discretization VLAs cannot be directly applied to this new continuous dynamics. We introduce FlowHijack, the first backdoor attack framework to systematically target the underlying vector-field dynamics of flow-matching VLAs. Our method combines a novel $\tau$-conditioned injection strategy, which manipulates the initial phase of the action generation, with a dynamics mimicry regularizer. Experiments demonstrate that FlowHijack achieves high attack success rates using stealthy, context-aware triggers where prior works failed. Crucially, it preserves benign task performance and, by enforcing kinematic similarity, generates malicious actions that are behaviorally indistinguishable from normal actions. Our findings reveal a significant vulnerability in continuous embodied models, highlighting the urgent need for defenses targeting the model's internal generative dynamics.