mlsanityData to 14 Oct 2026

Optimizing Model Splitting and Device Task Assignment for Deceptive Signal Assisted Private Multi-hop Split Learning

arXiv 2507.07323 ↗First posted 9 Jul 2025cs.LGcited by 3

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

Abstract (arXiv)

In this paper, deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdroppers from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the information leaked to eavesdroppers while meeting the model training energy consumption and delay constraints. To solve this problem, we propose a soft actor-critic deep reinforcement learning framework with intrinsic curiosity module and cross-attention (ICM-CA) that enables a centralized agent to determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device without knowing the position and monitoring probability of eavesdroppers. The proposed method uses an ICM module to encourage the server to explore novel actions and states and a CA module to determine the importance of each historical state-action pair thus improving training efficiency. Simulation results demonstrate that the proposed method improves the convergence rate by up to 3x and reduces the information leaked to eavesdroppers by up to 13% compared to the traditional SAC algorithm.

Key facts. Cited by 3 papers 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 20 of its 47 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

20 of 47 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2021Convex optimizationcited by 2,515
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  5. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  6. 2018Large-Scale Study of Curiosity-Driven Learningcited by 280
  7. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
  8. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  9. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  10. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 127
  11. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  12. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
8 more
  1. 2022Split Learning over Wireless Networks: Parallel Design and Resource Managementcited by 75
  2. 2024A Survey of Recent Advances in Optimization Methods for Wireless Communicationscited by 19
  3. 2023Accelerating Split Federated Learning over Wireless Communication Networkscited by 16
  4. 2024LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classificationcited by 11
  5. 2023Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learningcited by 9
  6. 2022Over-the-Air Split Machine Learning in Wireless MIMO Networkscited by 7
  7. 2024Split Federated Learning Over Heterogeneous Edge Devices: Algorithm and Optimizationcited by 4
  8. 2023SplitMAC: Wireless Split Learning over Multiple Access Channelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Contrastive Language-Image Pre-Training Model based Semantic Communication Performance Optimizationcited by 2
  2. 2026A Secure and Private Distributed Bayesian Federated Learning Designcited by 1
  3. 2026Optimizing Reinforcement Learning Training over Digital Twin Enabled Multi-fidelity Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference
  2. 2026LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections
  3. 2021Communication and Computation Reduction for Split Learning using Asynchronous Training
  4. 2024Differentially Private Deep Model-Based Reinforcement Learning
  5. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
  6. 2021Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners
  7. 2025Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
  8. 2024Decentralized Covert Routing in Heterogeneous Networks Using Reinforcement Learning