mlsanityData to 14 Oct 2026

PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning

arXiv 2403.05864 ↗First posted 9 Mar 2024cs.LG cs.CR cs.HCcited by 1

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

In human-centric Cyber-Physical Systems (CPS), personalized Deep Reinforcement Learning (DRL) agents must share fine-grained control actions with cloud services, exposing sensitive private states to inference attacks by honest-but-curious adversaries. Static privacy models fail to address the dynamic nature of human interactions. This paper introduces PEARL (Personalized Early-exit Adaptive Reinforcement Learning), a novel framework that addresses this challenge through structural privacy control rather than data perturbation. PEARL deploys a dual-path Early-Exit Deep Q-Network (EE-DQN) at the edge, using Mutual Information (MI) between private states and observable actions to train per-branch binary labels: Utility Confidence Labels (UCL), verifying action quality, and Privacy Confidence Labels (PCL), verifying MI leakage remains below a user-defined threshold. At inference, PEARL selects the shallowest exit branch satisfying both UCL and PCL, structurally limiting shared action descriptive power without noise injection. An MI-based feedback loop tracks behavioral drift and triggers retraining when privacy-utility profiles shift, ensuring long-term robustness. Validated on a personalized smart-home HVAC system and a VR smart classroom, PEARL reduces adversarial state-inference accuracy by 25.67% on average with a controlled 10-16% utility cost, establishing a practical, dynamically enforceable privacy-utility tradeoff.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 7 of its 46 references that are in the map. First posted on arXiv 9 Mar 2024.

Builds on

7 of 46 references.

References · 7

  1. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  2. 2016Cooperative Inverse Reinforcement Learningcited by 300
  3. 2019Privacy-preserving Q-Learning with Functional Noise in Continuous State Spacescited by 30
  4. 2022Auditing Membership Leakages of Multi-Exit Networkscited by 27
  5. 2021FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoTcited by 15
  6. 2023adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systemscited by 6
  7. 2023ERUDITE: Human-in-the-Loop IoT for an Adaptive Personalized Learning Systemcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Riskcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling
  2. 2025Efficient Implementation of Reinforcement Learning over Homomorphic Encryption
  3. 2025Towards User-level Private Reinforcement Learning with Human Feedback
  4. 2025Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning
  5. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
  6. 2026Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference
  7. 2025Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
  8. 2026Privacy Preserving Reinforcement Learning with One-Sided Feedback