Resilient Collaborative Intelligence for Adversarial IoT Environments
Many IoT networks, including for battlefield deployments, involve the deployment of resource-constrained sensors with varying degrees of redundancy/overlap (i.e., their data streams possess significant spatiotemporal correlation). Collaborative intelligence, whereby individual nodes adjust their inf...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2019
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4429 https://ink.library.smu.edu.sg/context/sis_research/article/5432/viewcontent/5._Resilient_Collaborative_Intelligence_for_Adversarial_IoT_Environments__FUSION2019_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-5432 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-54322020-04-23T04:36:29Z Resilient Collaborative Intelligence for Adversarial IoT Environments WEERAKOON, Dulanga JAYARAJAH, Kasthuri TANDRIANSYAH, Randy MISRA, Archan Many IoT networks, including for battlefield deployments, involve the deployment of resource-constrained sensors with varying degrees of redundancy/overlap (i.e., their data streams possess significant spatiotemporal correlation). Collaborative intelligence, whereby individual nodes adjust their inferencing pipelines to incorporate such correlated observations from other nodes, can improve both inferencing accuracy and performance metrics (such as latency and energy overheads). Using realworld data from a multicamera deployment, we first demonstrate the significant performance gains (up to 14% increase in accuracy) from such collaborative intelligence, achieved through two different approaches: (a) one involving statistical fusion of outputs from different nodes, and (b) another involving the development of new collaborative deep neural networks (DNNs). We then show that these collaboration-driven performance gains susceptible to adversarial behavior by one or more nodes, and thus need resilient mechanisms to provide robustness against such malicious behavior. We also introduce an underdevelopment testbed at SMU, specifically designed to enable realworld experimentation with such collaborative IoT intelligence techniques. 2019-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4429 https://ink.library.smu.edu.sg/context/sis_research/article/5432/viewcontent/5._Resilient_Collaborative_Intelligence_for_Adversarial_IoT_Environments__FUSION2019_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Constrained sensors Correlated observations Energy overheads IOT networks Multi-cameras Performance Gain Performance metrics Spatiotemporal correlation Artificial Intelligence and Robotics Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Constrained sensors Correlated observations Energy overheads IOT networks Multi-cameras Performance Gain Performance metrics Spatiotemporal correlation Artificial Intelligence and Robotics Software Engineering |
spellingShingle |
Constrained sensors Correlated observations Energy overheads IOT networks Multi-cameras Performance Gain Performance metrics Spatiotemporal correlation Artificial Intelligence and Robotics Software Engineering WEERAKOON, Dulanga JAYARAJAH, Kasthuri TANDRIANSYAH, Randy MISRA, Archan Resilient Collaborative Intelligence for Adversarial IoT Environments |
description |
Many IoT networks, including for battlefield deployments, involve the deployment of resource-constrained sensors with varying degrees of redundancy/overlap (i.e., their data streams possess significant spatiotemporal correlation). Collaborative intelligence, whereby individual nodes adjust their inferencing pipelines to incorporate such correlated observations from other nodes, can improve both inferencing accuracy and performance metrics (such as latency and energy overheads). Using realworld data from a multicamera deployment, we first demonstrate the significant performance gains (up to 14% increase in accuracy) from such collaborative intelligence, achieved through two different approaches: (a) one involving statistical fusion of outputs from different nodes, and (b) another involving the development of new collaborative deep neural networks (DNNs). We then show that these collaboration-driven performance gains susceptible to adversarial behavior by one or more nodes, and thus need resilient mechanisms to provide robustness against such malicious behavior. We also introduce an underdevelopment testbed at SMU, specifically designed to enable realworld experimentation with such collaborative IoT intelligence techniques. |
format |
text |
author |
WEERAKOON, Dulanga JAYARAJAH, Kasthuri TANDRIANSYAH, Randy MISRA, Archan |
author_facet |
WEERAKOON, Dulanga JAYARAJAH, Kasthuri TANDRIANSYAH, Randy MISRA, Archan |
author_sort |
WEERAKOON, Dulanga |
title |
Resilient Collaborative Intelligence for Adversarial IoT Environments |
title_short |
Resilient Collaborative Intelligence for Adversarial IoT Environments |
title_full |
Resilient Collaborative Intelligence for Adversarial IoT Environments |
title_fullStr |
Resilient Collaborative Intelligence for Adversarial IoT Environments |
title_full_unstemmed |
Resilient Collaborative Intelligence for Adversarial IoT Environments |
title_sort |
resilient collaborative intelligence for adversarial iot environments |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2019 |
url |
https://ink.library.smu.edu.sg/sis_research/4429 https://ink.library.smu.edu.sg/context/sis_research/article/5432/viewcontent/5._Resilient_Collaborative_Intelligence_for_Adversarial_IoT_Environments__FUSION2019_.pdf |
_version_ |
1770574767263318016 |