Buchumschlag

Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policies

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Fan, Junchao, Lei, Xuyang, Chang, Xiaolin
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
von: Fan, Junchao, et al.
Veröffentlicht: (2024)

Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
von: Fan, Junchao, et al.
Veröffentlicht: (2025)

Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
von: Wei, Qi, et al.
Veröffentlicht: (2026)

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
von: Ju, Bocheng, et al.
Veröffentlicht: (2025)

EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
von: Jiao, Siwen, et al.
Veröffentlicht: (2025)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
von: Zhong, Xuyang, et al.
Veröffentlicht: (2025)

HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
von: Huang, Zilin, et al.
Veröffentlicht: (2024)

Adversarial Training for Defense Against Label Poisoning Attacks
von: Bal, Melis Ilayda, et al.
Veröffentlicht: (2025)

Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
von: Sun, Xiaolin, et al.
Veröffentlicht: (2025)

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

Attack End-to-End Autonomous Driving through Module-Wise Noise
von: Wang, Lu, et al.
Veröffentlicht: (2024)

Deep Adversarial Defense Against Multilevel-Lp Attacks
von: Wang, Ren, et al.
Veröffentlicht: (2024)

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

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

GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
von: Cui, Canyixing, et al.
Veröffentlicht: (2026)

Beyond Distribution Sharpening: The Importance of Task Rewards
von: Mittal, Sarthak, et al.
Veröffentlicht: (2026)

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

CAMA: Exploring Collusive Adversarial Attacks in c-MARL
von: Niu, Men, et al.
Veröffentlicht: (2026)

A White-Box Adversarial Attack Against a Digital Twin
von: Patterson, Wilson, et al.
Veröffentlicht: (2022)

TimeDRL: Disentangled Representation Learning for Multivariate Time-Series
von: Chang, Ching, et al.
Veröffentlicht: (2023)

ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
von: Nie, Tong, et al.
Veröffentlicht: (2026)

Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification
von: Luo, Jiayi, et al.
Veröffentlicht: (2025)

Optimal Defenses Against Gradient Reconstruction Attacks
von: Chen, Yuxiao, et al.
Veröffentlicht: (2024)

Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
von: Cao, Haifang, et al.
Veröffentlicht: (2026)

Robust Decision Aggregation with Adversarial Experts
von: Guo, Yongkang, et al.
Veröffentlicht: (2024)

DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services
von: Lin, Youfang, et al.
Veröffentlicht: (2024)

Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
von: Gupta, Aditi, et al.
Veröffentlicht: (2026)

Adversarial Attacks on Hyperbolic Networks
von: van Spengler, Max, et al.
Veröffentlicht: (2024)

Safe and Economical UAV Trajectory Planning in Low-Altitude Airspace: A Hybrid DRL-LLM Approach with Compliance Awareness
von: Gong, Yanwei, et al.
Veröffentlicht: (2025)

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
von: Yamamura, Keiichiro, et al.
Veröffentlicht: (2024)

Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction
von: Badkul, Amitesh, et al.
Veröffentlicht: (2025)

Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space
von: Golchoubian, Mahsa, et al.
Veröffentlicht: (2024)

ARMOR: Adaptive Resilience Against Model Poisoning Attacks in Continual Federated Learning for Mobile Indoor Localization
von: Gufran, Danish, et al.
Veröffentlicht: (2026)

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

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
von: Kang, Hyungkyu, et al.
Veröffentlicht: (2025)

Dynamic Mixture of Experts Against Severe Distribution Shifts
von: Kim, Donghu
Veröffentlicht: (2025)

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)

How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness
von: Rossolini, Giulio
Veröffentlicht: (2026)

AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles
von: Salek, M Sabbir, et al.
Veröffentlicht: (2023)

TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
von: He, Zhipeng, et al.
Veröffentlicht: (2025)