Imagen de Portada

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Xiangyu, Deng, Chenghao, Sun, Yanchao, Liang, Yongyuan, Huang, Furong
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
por: Liang, Yongyuan, et al.
Publicado: (2023)

Is poisoning a real threat to LLM alignment? Maybe more so than you think
por: Pathmanathan, Pankayaraj, et al.
Publicado: (2024)

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
por: Xu, Yuancheng, et al.
Publicado: (2023)

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
por: Wang, Xiyao, et al.
Publicado: (2023)

Towards the Worst-case Robustness of Large Language Models
por: Chen, Huanran, et al.
Publicado: (2025)

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
por: Miao, Changhao, et al.
Publicado: (2026)

Contextual Decision-Making with Knapsacks Beyond the Worst Case
por: Chen, Zhaohua, et al.
Publicado: (2022)

Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization
por: Satheesh, Anirudh, et al.
Publicado: (2026)

ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
por: Ji, Tianying, et al.
Publicado: (2024)

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
por: Xu, Yuancheng, et al.
Publicado: (2024)

Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
por: Aryal, Manish, et al.
Publicado: (2026)

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

Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
por: Panaitescu-Liess, Michael-Andrei, et al.
Publicado: (2025)

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
por: Zheng, Ruijie, et al.
Publicado: (2024)

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

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
por: Wang, Kaixin, et al.
Publicado: (2023)

RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization
por: Xia, Linxuan, et al.
Publicado: (2026)

Explainable Clustering Beyond Worst-Case Guarantees
por: Fleissner, Maximilian, et al.
Publicado: (2024)

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers
por: Jin, Gaojie, et al.
Publicado: (2025)

Distribution Learning with Valid Outputs Beyond the Worst-Case
por: Rittler, Nick, et al.
Publicado: (2024)

Worst-case generation via minimax optimization in Wasserstein space
por: Cheng, Xiuyuan, et al.
Publicado: (2025)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
por: Zhang, Shenao, et al.
Publicado: (2025)

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
por: Djilani, Mohamed, et al.
Publicado: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
por: Wang, Chen, et al.
Publicado: (2025)

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
por: Ding, Mucong, et al.
Publicado: (2024)

Alpha and Prejudice: Improving $α$-sized Worst-case Fairness via Intrinsic Reweighting
por: Li, Jing, et al.
Publicado: (2024)

Worst-case low-rank approximations
por: Fries, Anya, et al.
Publicado: (2026)

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
por: Fu, Yanzhang, et al.
Publicado: (2026)

LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
por: Wong, Zhen Hao, et al.
Publicado: (2025)

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
por: Zhu, Taojie, et al.
Publicado: (2026)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
por: Zhan, Qiusi, et al.
Publicado: (2025)

AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning
por: Tang, Zehui, et al.
Publicado: (2026)

Memorization With Neural Nets: Going Beyond the Worst Case
por: Dirksen, Sjoerd, et al.
Publicado: (2023)

Natural Policy Gradient for Average Reward Non-Stationary RL
por: Jali, Neharika, et al.
Publicado: (2025)

Adaptive Sampling and Clipping for Private Worst-Case Group Optimization
por: Cairney-Leeming, Max, et al.
Publicado: (2026)

KCES: Training-Free Defense for Robust Graph Neural Networks via Kernel Complexity
por: Jia, Yaning, et al.
Publicado: (2025)

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
por: Ye, Chenlu, et al.
Publicado: (2026)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
por: Agrawal, Aakriti, et al.
Publicado: (2024)

Dynamic Data Layout Optimization with Worst-case Guarantees
por: Rong, Kexin, et al.
Publicado: (2024)