StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots
cs.RO, cs.AI, cs.CR
Submitted: 2026-08-07
Updated: 2026-08-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Qwen3-VL Technical Report
- RT-1: Robotics Transformer for Real-World Control at Scale
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- PaLM-E: An Embodied Multimodal Language Model
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- OpenVLA: An Open-Source Vision-Language-Action Model
- Compromising Embodied Agents with Contextual Backdoor Attacks
- Terrain Recognition and Contact Force Estimation through a Sensorized Paw for Legged Robots
- Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving