SARSA based access control with approximation by TileCoding

Traditional sensor nodes ignore the packet loss rate during information transmission and the access control security problem caused by server utilization when uploading data. To solve the problem, we propose a SARSA based access control method with approximation by TileCoding (SACT), which takes the sensor packet loss rate and the server error rate into account. The network state is estimated by the packet loss rate and variable bit error rate to get a server access control strategy to improve security performance. The eventual strategy complies with the minimum information loss and the maximum server utilization. Results of experiments show that the algorithm is capable of achieving good results in the total amount of information received by the server system. The SACT improves the server utilization rate and the overall security performance of the network.

[1]  Joshua B. Tenenbaum,et al.  Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation , 2016, NIPS.

[2]  Matthias Althoff,et al.  Combining zonotopes and support functions for efficient reachability analysis of linear systems , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[3]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[4]  Andreas Jacobsson,et al.  A risk analysis of a smart home automation system , 2016, Future Gener. Comput. Syst..

[5]  Imran Khan,et al.  Wireless sensor network virtualization: A survey , 2015, IEEE Communications Surveys & Tutorials.

[6]  Shan Wang,et al.  A Survey of Extended Role-Based Access Control in Cloud Computing , 2015 .

[7]  David Grace,et al.  Application of reinforcement learning on medium access control for wireless sensor networks , 2013 .

[8]  Sriram Subramaniam,et al.  A Bayesian network model of the bit error rate for cognitive radio networks , 2015, 2015 IEEE 16th Annual Wireless and Microwave Technology Conference (WAMICON).

[9]  E. Lutz,et al.  Information Gain and Loss for a Quantum Maxwell's Demon. , 2018, Physical review letters.

[10]  Parham Moradi,et al.  Reinforcement Learning for Multiple Access Control in Wireless Sensor Networks: Review, Model, and Open Issues , 2013, Wireless Personal Communications.

[11]  Tong Boon Tang,et al.  Vehicle Detection Techniques for Collision Avoidance Systems: A Review , 2015, IEEE Transactions on Intelligent Transportation Systems.

[12]  H. Pham,et al.  Bellman equation and viscosity solutions for mean-field stochastic control problem , 2015, 1512.07866.

[13]  Joan Serrat,et al.  Management and orchestration challenges in network functions virtualization , 2016, IEEE Communications Magazine.

[14]  Ngai-Man Cheung,et al.  Embedding Based on Function Approximation for Large Scale Image Search , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Nhien-An Le-Khac,et al.  Collective Anomaly Detection Based on Long Short-Term Memory Recurrent Neural Networks , 2016, FDSE.

[16]  Stefano Paraboschi,et al.  SeSQLite: Security Enhanced SQLite: Mandatory Access Control for Android databases , 2015, ACSAC 2015.

[17]  Shay Gueron,et al.  Fast prime field elliptic-curve cryptography with 256-bit primes , 2014, Journal of Cryptographic Engineering.

[18]  Tom Schaul,et al.  Universal Value Function Approximators , 2015, ICML.

[19]  M. Serrão,et al.  Computer vision and GIS for the navigation of blind persons in buildings , 2013, Universal Access in the Information Society.

[20]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[21]  Chao Wang,et al.  A Novel Dynamic Spectrum Access Framework Based on Reinforcement Learning for Cognitive Radio Sensor Networks , 2016, Sensors.

[22]  J. D. Ultra,et al.  A simple model of separation of duty for access control models , 2017, Comput. Secur..

[23]  Wei Wei.  Classical optimal planning method based on compacted encodings , 2010 .

[24]  Daniel M. Hartung,et al.  Effects of a prior authorization policy for extended‐release/long‐acting opioids on utilization and outcomes in a state Medicaid program , 2018, Addiction.

[25]  Renquan Lu,et al.  A New Design of Model Predictive Tracking Control for Networked Control System Under Random Packet Loss and Uncertainties , 2016, IEEE Transactions on Industrial Electronics.

[26]  Peter Stone,et al.  Deep Recurrent Q-Learning for Partially Observable MDPs , 2015, AAAI Fall Symposia.

[27]  Ram Krishnan,et al.  Attributes Enhanced Role-Based Access Control Model , 2015, TrustBus.

[28]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[29]  Ramaswamy Chandramouli,et al.  Extensible Access Control Markup Language (XACML) and Next Generation Access Control (NGAC) , 2016, ABAC '16.

[30]  Ping Wang,et al.  On the Challenges in Designing Identity-Based Privacy-Preserving Authentication Schemes for Mobile Devices , 2018, IEEE Systems Journal.

[31]  Abeba Mitiku Asfaw,et al.  The Impact of Training and Development on Employee Performance and Effectiveness: A Case Study of District Five Administration Office, Bole Sub-City, Addis Ababa, Ethiopia , 2015 .

[32]  Alex Zhavoronkov,et al.  Applications of Deep Learning in Biomedicine. , 2016, Molecular pharmaceutics.

[33]  David Silver,et al.  A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning , 2017, NIPS.

[34]  Haiying Shen,et al.  Distributed Autonomous Virtual Resource Management in Datacenters Using Finite-Markov Decision Process , 2014, IEEE/ACM Transactions on Networking.

[35]  Ravi S. Sandhu,et al.  Label-Based Access Control: An ABAC Model with Enumerated Authorization Policy , 2016, ABAC '16.

[36]  J. A. Villar,et al.  Status of the ANAIS Dark Matter Project at the Canfranc Underground Laboratory , 2015, 1508.07213.