Imagen de Portada

Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Jianyi, Wei, Yujie, Zhen, Ruichen, Zhao, Bo, Xia, Xiaobo, Shao, Rui, Su, Xiu, Yang, Shuo
Formato:	Preprint
Publicado:	2026
Materias:	Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching
por: Wei, Yujie, et al.
Publicado: (2026)

APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation
por: Zhang, Daoxuan, et al.
Publicado: (2026)

ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
por: Dai, Weisheng, et al.
Publicado: (2026)

AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
por: Kong, Weijie, et al.
Publicado: (2026)

Adaptive Capacity Allocation for Vision Language Action Fine-tuning
por: Kim, Donghoon, et al.
Publicado: (2026)

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
por: Li, Wenhao, et al.
Publicado: (2026)

Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
por: Liang, Yuanchang, et al.
Publicado: (2026)

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
por: Li, Hengtao, et al.
Publicado: (2025)

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
por: Sun, Ming, et al.
Publicado: (2026)

See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations
por: Chen, Guangyan, et al.
Publicado: (2025)

ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
por: Liu, Zhenyang, et al.
Publicado: (2026)

TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
por: Chen, Zengjue, et al.
Publicado: (2025)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
por: Li, Chengmeng, et al.
Publicado: (2025)

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
por: Xu, Zonghuan, et al.
Publicado: (2025)

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
por: Xu, Bingxin, et al.
Publicado: (2026)

ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
por: Zhang, Daoxuan, et al.
Publicado: (2026)

Robotic-CLIP: Fine-tuning CLIP on Action Data for Robotic Applications
por: Nguyen, Nghia, et al.
Publicado: (2024)

Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
por: Wulff, Theodor, et al.
Publicado: (2026)

VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
por: Chen, Guanyan, et al.
Publicado: (2024)

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
por: Hu, Xintong, et al.
Publicado: (2026)

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
por: Huang, Dongchi, et al.
Publicado: (2025)

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
por: Zhang, Tonghe, et al.
Publicado: (2025)

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
por: Yang, Rushuai, et al.
Publicado: (2025)

Multi-AGV Path Planning Method via Reinforcement Learning and Particle Filters
por: Shuo, Shao
Publicado: (2024)

TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video
por: Zhou, Jianyi, et al.
Publicado: (2026)

ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
por: Ye, Shuhao, et al.
Publicado: (2025)

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
por: Wang, Yihao, et al.
Publicado: (2025)

UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigation
por: Wang, Zhangyuan, et al.
Publicado: (2025)

VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation
por: Zhang, Chaofan, et al.
Publicado: (2025)

StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
por: Deng, Shengliang, et al.
Publicado: (2025)

LAOF: Robust Latent Action Learning with Optical Flow Constraints
por: Bu, Xizhou, et al.
Publicado: (2025)

STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models
por: Xu, Feng, et al.
Publicado: (2025)

Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane Change
por: Xu, Ruichen, et al.
Publicado: (2024)

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
por: Lyu, Mingyang, et al.
Publicado: (2025)

RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback
por: Shu, Junyang, et al.
Publicado: (2025)

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
por: Li, Wei, et al.
Publicado: (2025)

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
por: Yang, Siyuan, et al.
Publicado: (2025)

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
por: Li, Qi, et al.
Publicado: (2026)

From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems
por: Xie, Mingyang, et al.
Publicado: (2026)

Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models
por: Xia, Xingyu, et al.
Publicado: (2026)