Presentation 2020-12-11
A Preliminary Multi-Agent Reinforcement Learning Approach for Responding Dynamic Traffic in Communication Destination Anonymization
Keita Sugiyama, Naoki Fukuta,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we describe our prototype mechanism using the simulation-based multi-agent reinforcement learning for automatically allocating resources for anonymizing communication destinations as one of the applications of the multi-agent techniques for network virtualization. As an example of concrete scenarios, we assume a network where end-hosts are connected frequently and traffic trends change frequently for this reason. In this scenario, we implement a mechanism that allows multiple agents represented by network switches to cooperate with other agents autonomously for adjusting the level of anonymity using multi-agent reinforcement learning, and confirm the effect by simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multi-Agent Reinforcement Learning / Moving Target Defense / Network Security
Paper # AI2020-10
Date of Issue 2020-12-03 (AI)

Conference Information
Committee AI
Conference Date 2020/12/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online and HAMAMATSU ACT CITY
Topics (in Japanese) (See Japanese page)
Topics (in English) Foundations and application technologies for AI systems on the new normal
Chair Naoki Fukuta(Shizuoka Univ.)
Vice Chair Yuichi Sei(Univ. of Electro-Comm.) / Yuko Sakurai(AIST)
Secretary Yuichi Sei(Nagoya Inst. of Tech.) / Yuko Sakurai(Tokyo Univ. of Agriculture and Technology)
Assistant

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Preliminary Multi-Agent Reinforcement Learning Approach for Responding Dynamic Traffic in Communication Destination Anonymization
Sub Title (in English)
Keyword(1) Multi-Agent Reinforcement Learning
Keyword(2) Moving Target Defense
Keyword(3) Network Security
1st Author's Name Keita Sugiyama
1st Author's Affiliation Shizuoka University(Shizuoka Univ.)
2nd Author's Name Naoki Fukuta
2nd Author's Affiliation Shizuoka University(Shizuoka Univ.)
Date 2020-12-11
Paper # AI2020-10
Volume (vol) vol.120
Number (no) AI-281
Page pp.pp.46-51(AI),
#Pages 6
Date of Issue 2020-12-03 (AI)