No article text was recorded for this version.
input perturbation sensitivity
Version 2 of 2360 papers620 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Adversarial Robust Deep Reinforcement Learning is Neither Robust Nor Safe
- Blog: Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information
- Blog: Adversarial attacks on reinforcement learning agents for command and control
- Blog: Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations
- Blog: Adversarial Attacks on Neural Network Policies
- Blog: Adversarial Attacks on Neural Network Policies
- Blog: Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
- Blog: Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
- Blog: Reinforcement Learning for Autonomous Defence in Software-Defined Networking
- Blog: Short Paper: Effects of Poisoning Attacks on Causal Deep Reinforcement Learning
- Blog: Adversarial Reinforcement Learning under Partial Observability in Software-Defined Networking
- Blog: Understanding adversarial attacks on observations in deep reinforcement learning
- Blog: PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
- Blog: Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
- Blog: Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
- Blog: Adversarial Attacks on Neural Network Policies
- Blog: Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
- Blog: Adaptive Reward-Poisoning Attacks against Reinforcement Learning
- Blog: Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
- Blog: Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
- Blog: Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
- Blog: Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning
- Blog: Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
- Blog: A Survey on Reinforcement Learning Security with Application to Autonomous Driving
- Blog: Observed Adversaries in Deep Reinforcement Learning
- Blog: Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning
- Blog: PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
- Blog: FullCycle: Full Stage Adversarial Attack For Reinforcement Learning Robustness Evaluation
- Blog: CopyCAT: Taking Control of Neural Policies with Constant Attacks
- Blog: Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics
- Blog: Minimalistic Attacks: How Little It Takes to Fool Deep Reinforcement Learning Policies
- Blog: Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
- Blog: On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks
- Blog: CopyCAT: : Taking Control of Neural Policies with Constant Attacks
- Blog: Delving into adversarial attacks on deep policies
- Blog: Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding
- Blog: Adversary Agnostic Robust Deep Reinforcement Learning
- Blog: Efficient and Robust Reinforcement Learning from Human Feedback
- Blog: Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
- Blog: Offline Reward Perturbation Boosts Distributional Shift in Online RL
- Blog: Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
- Blog: Sequential Attacks on Agents for Long-Term Adversarial Goals
- Blog: Investigating Vulnerabilities of Deep Neural Policies
- Blog: Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
- Blog: Adversarial Cheap Talk
- Blog: Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
- Blog: Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
- Blog: Enhanced Adversarial Strategically-Timed Attacks Against Deep Reinforcement Learning
- Blog: Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
- Blog: ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
- Blog: Reinforcement Learning for feedback-enabled cyber resilience
- Blog: Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
- Blog: Policy Poisoning in Batch Reinforcement Learning and Control
- Blog: On the Robustness of Safe Reinforcement Learning under Observational Perturbations
- Blog: Adversarial poisoning attacks on reinforcement learning-driven energy pricing
- Blog: Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
- Blog: Corruption-Robust Offline Reinforcement Learning with General Function Approximation
- Blog: Adversarial Policies: Attacking Deep Reinforcement Learning
- Blog: Non-Robust Feature Mapping in Deep Reinforcement Learning
- Blog: Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
Showing 60 of 360 papers.
History & citation
Current · Permanent link
- Targeted Behavior Manipulation in Reinforcement Learning merged into this direction (68% overlap)
- Geometric Robustness Against Reward Poisoning in Linear Environments merged into this direction (60% overlap)
- Strategically Timed Sparse Attacks on Reinforcement Learning merged into this direction (50% overlap)
- Black-Box Data Poisoning for Online Reinforcement Learning merged into this direction (56% overlap)
- Adversarial Reinforcement Learning as a POMDP merged into this direction (55% overlap)
- Optimal Sequential Attacks on Reinforcement Learning Policies merged into this direction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_input_perturbation_sensitivity_0f8be910,
title = {input perturbation sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/input-perturbation-sensitivity/rdr_0f8be9105a5a4f12b06459dae5f3a2e7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_input_perturbation_sensitivity_0f8be910_v2,
title = {input perturbation sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/input-perturbation-sensitivity/rdr_0f8be9105a5a4f12b06459dae5f3a2e7/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}