Copertina

How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kalra, Akansha, Patil, Basavasagar, Tao, Guanhong, Brown, Daniel S.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dataset Poisoning Attacks on Behavioral Cloning Policies
di: Kalra, Akansha, et al.
Pubblicazione: (2025)

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

Learning-based Detection of GPS Spoofing Attack for Quadrotors
di: Wang, Pengyu, et al.
Pubblicazione: (2025)

Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
di: Rathbun, Ethan, et al.
Pubblicazione: (2026)

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks
di: Dash, Pritam, et al.
Pubblicazione: (2025)

Secure Control Systems for Autonomous Quadrotors against Cyber-Attacks
di: Belkadi, Samuel
Pubblicazione: (2024)

ARBoids: Adaptive Residual Reinforcement Learning With Boids Model for Cooperative Multi-USV Target Defense
di: Tao, Jiyue, et al.
Pubblicazione: (2025)

Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
di: Chanda, Dibaloke, et al.
Pubblicazione: (2023)

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
di: Zhu, Rui, et al.
Pubblicazione: (2023)

Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard
di: Wong, Henry, et al.
Pubblicazione: (2025)

Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defend
di: Liu, Yige, et al.
Pubblicazione: (2026)

Adversarial Attacks on Graph Neural Networks via Meta Learning
di: Zügner, Daniel, et al.
Pubblicazione: (2019)

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

A Geometric Framework for Adversarial Vulnerability in Machine Learning
di: Bell, Brian
Pubblicazione: (2024)

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
di: Fang, Junyuan, et al.
Pubblicazione: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
di: Peng, Jinjia, et al.
Pubblicazione: (2025)

Using Temperature Sampling to Effectively Train Robot Learning Policies on Imbalanced Datasets
di: Patil, Basavasagar, et al.
Pubblicazione: (2025)

Adversarial Attacks on Transformers-Based Malware Detectors
di: Jakhotiya, Yash, et al.
Pubblicazione: (2022)

Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
di: Roy, Samrendra, et al.
Pubblicazione: (2026)

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
di: Jiang, Enyi, et al.
Pubblicazione: (2024)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
di: Jin, Zhibo, et al.
Pubblicazione: (2024)

Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes
di: Hamidi, Shayan Mohajer, et al.
Pubblicazione: (2024)

Adversarial Contrastive Learning for LLM Quantization Attacks
di: Song, Dinghong, et al.
Pubblicazione: (2026)

Temporal Analysis of Adversarial Attacks in Federated Learning
di: Mapakshi, Rohit, et al.
Pubblicazione: (2025)

Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
di: Peng, Qizhou, et al.
Pubblicazione: (2025)

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security
di: Gibson, Marsalis, et al.
Pubblicazione: (2024)

Effective Universal Unrestricted Adversarial Attacks using a MOE Approach
di: Baia, A. E., et al.
Pubblicazione: (2021)

Low Rank Adaptation for Adversarial Perturbation
di: Liu, Han, et al.
Pubblicazione: (2026)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
di: Lobo, Elita, et al.
Pubblicazione: (2024)

Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting
di: Chichifoi, Karina, et al.
Pubblicazione: (2025)

Adversarial Inception Backdoor Attacks against Reinforcement Learning
di: Rathbun, Ethan, et al.
Pubblicazione: (2024)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
di: Yan, Xinhai, et al.
Pubblicazione: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
di: Zhang, Junrui, et al.
Pubblicazione: (2025)

Passive Inference Attacks on Split Learning via Adversarial Regularization
di: Zhu, Xiaochen, et al.
Pubblicazione: (2023)

Manipulating Trajectory Prediction with Backdoors
di: Messaoud, Kaouther, et al.
Pubblicazione: (2023)

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
di: Haldar, Rajdeep, et al.
Pubblicazione: (2024)

Rethinking the Evaluation of Secure Code Generation
di: Dai, Shih-Chieh, et al.
Pubblicazione: (2025)

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
di: Zheng, Rui, et al.
Pubblicazione: (2024)

TA3: Testing Against Adversarial Attacks on Machine Learning Models
di: Jin, Yuanzhe, et al.
Pubblicazione: (2024)

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
di: Bertran, Martin, et al.
Pubblicazione: (2024)