Buchumschlag

Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhao, Ke, Huang, Huayang, Li, Miao, Wu, Yu
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Artificial Intelligence Robotics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
von: Zhang, Zongyuan, et al.
Veröffentlicht: (2025)

Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
von: Zhao, Albert, et al.
Veröffentlicht: (2025)

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

DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
von: Guo, Ke, et al.
Veröffentlicht: (2025)

Diffusion-Reward Adversarial Imitation Learning
von: Lai, Chun-Mao, et al.
Veröffentlicht: (2024)

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
von: Xu, Charles, et al.
Veröffentlicht: (2024)

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
von: Bai, Fengshuo, et al.
Veröffentlicht: (2024)

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
von: Zha, Lihan, et al.
Veröffentlicht: (2023)

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
von: Li, Yuanpeng, et al.
Veröffentlicht: (2026)

Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
von: Ravichandran, Zachary, et al.
Veröffentlicht: (2025)

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
von: Wang, Yixiao, et al.
Veröffentlicht: (2025)

Adversarial Attacks on Robotic Vision Language Action Models
von: Jones, Eliot Krzysztof, et al.
Veröffentlicht: (2025)

SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation
von: Stoler, Benjamin, et al.
Veröffentlicht: (2024)

Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
von: Nakanishi, Kosuke, et al.
Veröffentlicht: (2025)

KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Vehicle Trajectory Forecasting at Signalized Intersections
von: Wei, Chuheng, et al.
Veröffentlicht: (2024)

StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion
von: Ma, Le, et al.
Veröffentlicht: (2025)

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
von: Acero, Fernando, et al.
Veröffentlicht: (2024)

Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand Manipulation
von: Li, Lanpei, et al.
Veröffentlicht: (2024)

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
von: Liang, Anthony, et al.
Veröffentlicht: (2026)

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
von: Duan, Tianyang, et al.
Veröffentlicht: (2025)

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
von: Liu, Xiangyu, et al.
Veröffentlicht: (2023)

LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios
von: Peng, Mingxing, et al.
Veröffentlicht: (2025)

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples
von: Lukyanov, Kirill, et al.
Veröffentlicht: (2024)

Vision-Language Foundation Models as Effective Robot Imitators
von: Li, Xinghang, et al.
Veröffentlicht: (2023)

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety
von: Wang, Justin, et al.
Veröffentlicht: (2024)

Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments
von: Couto, Gustavo Claudio Karl, et al.
Veröffentlicht: (2023)

Reinforcement Learning via Auxiliary Task Distillation
von: Harish, Abhinav Narayan, et al.
Veröffentlicht: (2024)

Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
von: Lin, Fudong, et al.
Veröffentlicht: (2025)

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
von: Huang, Baixiao, et al.
Veröffentlicht: (2026)

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
von: Liu, Jun, et al.
Veröffentlicht: (2026)

Annealing Self-Distillation Rectification Improves Adversarial Training
von: Wu, Yu-Yu, et al.
Veröffentlicht: (2023)

Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
von: Li, Chenhao, et al.
Veröffentlicht: (2025)

Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
von: Levy, Jacob, et al.
Veröffentlicht: (2026)

Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
von: Li, Chenhao, et al.
Veröffentlicht: (2025)

EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly
von: Lai, Shih-Yu, et al.
Veröffentlicht: (2026)

Co-jump: Cooperative Jumping with Quadrupedal Robots via Multi-Agent Reinforcement Learning
von: Dong, Shihao, et al.
Veröffentlicht: (2026)

VLMgineer: Vision Language Models as Robotic Toolsmiths
von: Gao, George Jiayuan, et al.
Veröffentlicht: (2025)

Online Foundation Model Selection in Robotics
von: Li, Po-han, et al.
Veröffentlicht: (2024)

Learning Pareto Set for Multi-Objective Continuous Robot Control
von: Shu, Tianye, et al.
Veröffentlicht: (2024)

Interpretable Robot Control via Structured Behavior Trees and Large Language Models
von: Chekam, Ingrid Maéva, et al.
Veröffentlicht: (2025)