Cover Image

Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Xiao, Wu, Lingxuan, Wang, Lizhong, Ying, Chengyang, Su, Hang, Zhu, Jun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
by: Wu, Lingxuan, et al.
Published: (2024)

Self-Consistent Model-based Adaptation for Visual Reinforcement Learning
by: Zhou, Xinning, et al.
Published: (2025)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
by: Ying, Chengyang, et al.
Published: (2022)

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
by: Tan, Hengkai, et al.
Published: (2024)

Exploratory Diffusion Model for Unsupervised Reinforcement Learning
by: Ying, Chengyang, et al.
Published: (2025)

On the Reuse Bias in Off-Policy Reinforcement Learning
by: Ying, Chengyang, et al.
Published: (2022)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
by: Ying, Chengyang, et al.
Published: (2022)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
by: Yu, Yunrui, et al.
Published: (2026)

Task Aware Dreamer for Task Generalization in Reinforcement Learning
by: Ying, Chengyang, et al.
Published: (2023)

Robust Embodied Perception in Dynamic Environments via Disentangled Weight Fusion
by: Guo, Juncen, et al.
Published: (2026)

PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
by: Ying, Chengyang, et al.
Published: (2024)

MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
by: Liu, Yang, et al.
Published: (2024)

ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
by: Tan, Hengkai, et al.
Published: (2024)

CapGen:An Environment-Adaptive Generator of Adversarial Patches
by: Li, Chaoqun, et al.
Published: (2024)

Defensive Dual Masking for Robust Adversarial Defense
by: Yang, Wangli, et al.
Published: (2024)

Exploring the Robustness of Decision-Level Through Adversarial Attacks on LLM-Based Embodied Models
by: Liu, Shuyuan, et al.
Published: (2024)

H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation
by: Bi, Hongzhe, et al.
Published: (2025)

RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
by: Liu, Songming, et al.
Published: (2026)

Visual Environment-Interactive Planning for Embodied Complex-Question Answering
by: Lan, Ning, et al.
Published: (2025)

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
by: Chen, Huanran, et al.
Published: (2023)

Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision
by: Zhu, Lingyu, et al.
Published: (2022)

BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
by: Lin, Xuewu, et al.
Published: (2024)

Utilizing Adversarial Training for Robust Voltage Control: An Adaptive Deep Reinforcement Learning Method
by: Chung, Sungjoo, et al.
Published: (2026)

Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning
by: Luo, Zhengyi, et al.
Published: (2025)

IDEA: Invariant Defense for Graph Adversarial Robustness
by: Tao, Shuchang, et al.
Published: (2023)

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
by: Huang, Yao, et al.
Published: (2023)

Adversarial Examples in Environment Perception for Automated Driving (Review)
by: Yan, Jun, et al.
Published: (2025)

Heterogeneous Adversarial Play in Interactive Environments
by: Xu, Manjie, et al.
Published: (2025)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
by: Nguyen, Thanh, et al.
Published: (2024)

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
by: Zhang, Wenqi, et al.
Published: (2025)

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
by: Xu, Long, et al.
Published: (2025)

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
by: Wu, Zhewei, et al.
Published: (2024)

RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents
by: Yeke, Doguhuan, et al.
Published: (2026)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
by: Kang, Caixin, et al.
Published: (2023)

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments
by: Yang, Xiao, et al.
Published: (2025)

Embodied Instruction Following in Unknown Environments
by: Wu, Zhenyu, et al.
Published: (2024)

AIR-Embodied: An Efficient Active 3DGS-based Interaction and Reconstruction Framework with Embodied Large Language Model
by: Qi, Zhenghao, et al.
Published: (2024)

Adversarial Reinforcement Learning for Offensive and Defensive Agents in a Simulated Zero-Sum Network Environment
by: Shahid, Abrar, et al.
Published: (2025)

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
by: Yichao, Wu, et al.
Published: (2025)

Visual Adversarial Attacks and Defenses in the Physical World: A Survey
by: Wei, Xingxing, et al.
Published: (2022)