Loading…
Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels
Embedded devices leak information about their inner activity through power and EM side channels. A defender who measures this leakage can thus use it to monitor the device and ensure its control-flow integrity. Previous works have investigated the use of power and EM side channels for control-flow m...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Online Access: | Request full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | 226 |
container_issue | |
container_start_page | 218 |
container_title | |
container_volume | |
creator | Amar, Michael Navanesan, Lojenaa Sayakkara, Asanka Oren, Yossi |
description | Embedded devices leak information about their inner activity through power and EM side channels. A defender who measures this leakage can thus use it to monitor the device and ensure its control-flow integrity. Previous works have investigated the use of power and EM side channels for control-flow monitoring, but they have only used a single side channel at a time. In this paper, we propose an approach that integrates both power and EM side channels to detect deviations from the device's normal behavior. Our model takes inspiration from multimodal machine learning used in image and speech recognition, and uses an intermediate integration design which passes multiple input modalities in parallel through a single self-attention transformer network. We evaluate our model on an off-the-shelf device at multiple noise levels, and show that it outperforms models that use only a single channel as input. In particular, we show how the multimodal approach can improve trace classification and anomaly detection accuracies by up to 18% and 11 %, respectively, compared to power/EM-only approaches. Additionally, we show that our approach is superior over the early and late integration approaches currently used in multimodal side channel analysis work. We release our machine-learning architecture, including trained models based on real-world data, as an open-source repository. Our work highlights how advances in the wider field of machine learning can be used to improve the security of embedded systems. |
doi_str_mv | 10.1109/DSD64264.2024.00037 |
format | conference_proceeding |
fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10741719</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10741719</ieee_id><sourcerecordid>10741719</sourcerecordid><originalsourceid>FETCH-ieee_primary_107417193</originalsourceid><addsrcrecordid>eNqFy0trAjEUBeBYKNS2_oJ2cXddOb15jJl0WR-4EQpj1xL0qpFMIklg6L_vFLoXDpzFdw5jLxwrztG8L9rFTImZqgQKVSGi1CM2Mdo0skbZDKnv2FhozaeixuaBPeZ8QawlN2rMaNvHtwzz2F09dRTKB2xicCUmF07QxmPpbaLBQ0nRw8rHHr7zn33Gcoav2FMCGw6w9LQfJp09BSpuD607DLezDYF8fmb3R-szTf77ib2ultv5euqIaHdNrrPpZ8dRK665kTf4F1rkSKU</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels</title><source>IEEE Xplore All Conference Series</source><creator>Amar, Michael ; Navanesan, Lojenaa ; Sayakkara, Asanka ; Oren, Yossi</creator><creatorcontrib>Amar, Michael ; Navanesan, Lojenaa ; Sayakkara, Asanka ; Oren, Yossi</creatorcontrib><description>Embedded devices leak information about their inner activity through power and EM side channels. A defender who measures this leakage can thus use it to monitor the device and ensure its control-flow integrity. Previous works have investigated the use of power and EM side channels for control-flow monitoring, but they have only used a single side channel at a time. In this paper, we propose an approach that integrates both power and EM side channels to detect deviations from the device's normal behavior. Our model takes inspiration from multimodal machine learning used in image and speech recognition, and uses an intermediate integration design which passes multiple input modalities in parallel through a single self-attention transformer network. We evaluate our model on an off-the-shelf device at multiple noise levels, and show that it outperforms models that use only a single channel as input. In particular, we show how the multimodal approach can improve trace classification and anomaly detection accuracies by up to 18% and 11 %, respectively, compared to power/EM-only approaches. Additionally, we show that our approach is superior over the early and late integration approaches currently used in multimodal side channel analysis work. We release our machine-learning architecture, including trained models based on real-world data, as an open-source repository. Our work highlights how advances in the wider field of machine learning can be used to improve the security of embedded systems.</description><identifier>EISSN: 2771-2508</identifier><identifier>EISBN: 9798350380385</identifier><identifier>DOI: 10.1109/DSD64264.2024.00037</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Computer architecture ; Deep learning ; Em-bedded devices ; Machine learning ; Malware detection ; Monitoring ; Multi-model architecture ; Performance evaluation ; Power demand ; Security ; Side channel analysis ; Software ; Speech recognition ; Transformers</subject><ispartof>Proceedings (Euromicro Conference on Digital Systems Design), 2024, p.218-226</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10741719$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10741719$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Amar, Michael</creatorcontrib><creatorcontrib>Navanesan, Lojenaa</creatorcontrib><creatorcontrib>Sayakkara, Asanka</creatorcontrib><creatorcontrib>Oren, Yossi</creatorcontrib><title>Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels</title><title>Proceedings (Euromicro Conference on Digital Systems Design)</title><addtitle>DSD</addtitle><description>Embedded devices leak information about their inner activity through power and EM side channels. A defender who measures this leakage can thus use it to monitor the device and ensure its control-flow integrity. Previous works have investigated the use of power and EM side channels for control-flow monitoring, but they have only used a single side channel at a time. In this paper, we propose an approach that integrates both power and EM side channels to detect deviations from the device's normal behavior. Our model takes inspiration from multimodal machine learning used in image and speech recognition, and uses an intermediate integration design which passes multiple input modalities in parallel through a single self-attention transformer network. We evaluate our model on an off-the-shelf device at multiple noise levels, and show that it outperforms models that use only a single channel as input. In particular, we show how the multimodal approach can improve trace classification and anomaly detection accuracies by up to 18% and 11 %, respectively, compared to power/EM-only approaches. Additionally, we show that our approach is superior over the early and late integration approaches currently used in multimodal side channel analysis work. We release our machine-learning architecture, including trained models based on real-world data, as an open-source repository. Our work highlights how advances in the wider field of machine learning can be used to improve the security of embedded systems.</description><subject>Accuracy</subject><subject>Computer architecture</subject><subject>Deep learning</subject><subject>Em-bedded devices</subject><subject>Machine learning</subject><subject>Malware detection</subject><subject>Monitoring</subject><subject>Multi-model architecture</subject><subject>Performance evaluation</subject><subject>Power demand</subject><subject>Security</subject><subject>Side channel analysis</subject><subject>Software</subject><subject>Speech recognition</subject><subject>Transformers</subject><issn>2771-2508</issn><isbn>9798350380385</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2024</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNqFy0trAjEUBeBYKNS2_oJ2cXddOb15jJl0WR-4EQpj1xL0qpFMIklg6L_vFLoXDpzFdw5jLxwrztG8L9rFTImZqgQKVSGi1CM2Mdo0skbZDKnv2FhozaeixuaBPeZ8QawlN2rMaNvHtwzz2F09dRTKB2xicCUmF07QxmPpbaLBQ0nRw8rHHr7zn33Gcoav2FMCGw6w9LQfJp09BSpuD607DLezDYF8fmb3R-szTf77ib2ultv5euqIaHdNrrPpZ8dRK665kTf4F1rkSKU</recordid><startdate>20240828</startdate><enddate>20240828</enddate><creator>Amar, Michael</creator><creator>Navanesan, Lojenaa</creator><creator>Sayakkara, Asanka</creator><creator>Oren, Yossi</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20240828</creationdate><title>Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels</title><author>Amar, Michael ; Navanesan, Lojenaa ; Sayakkara, Asanka ; Oren, Yossi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_107417193</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Computer architecture</topic><topic>Deep learning</topic><topic>Em-bedded devices</topic><topic>Machine learning</topic><topic>Malware detection</topic><topic>Monitoring</topic><topic>Multi-model architecture</topic><topic>Performance evaluation</topic><topic>Power demand</topic><topic>Security</topic><topic>Side channel analysis</topic><topic>Software</topic><topic>Speech recognition</topic><topic>Transformers</topic><toplevel>online_resources</toplevel><creatorcontrib>Amar, Michael</creatorcontrib><creatorcontrib>Navanesan, Lojenaa</creatorcontrib><creatorcontrib>Sayakkara, Asanka</creatorcontrib><creatorcontrib>Oren, Yossi</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Amar, Michael</au><au>Navanesan, Lojenaa</au><au>Sayakkara, Asanka</au><au>Oren, Yossi</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels</atitle><btitle>Proceedings (Euromicro Conference on Digital Systems Design)</btitle><stitle>DSD</stitle><date>2024-08-28</date><risdate>2024</risdate><spage>218</spage><epage>226</epage><pages>218-226</pages><eissn>2771-2508</eissn><eisbn>9798350380385</eisbn><coden>IEEPAD</coden><abstract>Embedded devices leak information about their inner activity through power and EM side channels. A defender who measures this leakage can thus use it to monitor the device and ensure its control-flow integrity. Previous works have investigated the use of power and EM side channels for control-flow monitoring, but they have only used a single side channel at a time. In this paper, we propose an approach that integrates both power and EM side channels to detect deviations from the device's normal behavior. Our model takes inspiration from multimodal machine learning used in image and speech recognition, and uses an intermediate integration design which passes multiple input modalities in parallel through a single self-attention transformer network. We evaluate our model on an off-the-shelf device at multiple noise levels, and show that it outperforms models that use only a single channel as input. In particular, we show how the multimodal approach can improve trace classification and anomaly detection accuracies by up to 18% and 11 %, respectively, compared to power/EM-only approaches. Additionally, we show that our approach is superior over the early and late integration approaches currently used in multimodal side channel analysis work. We release our machine-learning architecture, including trained models based on real-world data, as an open-source repository. Our work highlights how advances in the wider field of machine learning can be used to improve the security of embedded systems.</abstract><pub>IEEE</pub><doi>10.1109/DSD64264.2024.00037</doi></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | EISSN: 2771-2508 |
ispartof | Proceedings (Euromicro Conference on Digital Systems Design), 2024, p.218-226 |
issn | 2771-2508 |
language | eng |
recordid | cdi_ieee_primary_10741719 |
source | IEEE Xplore All Conference Series |
subjects | Accuracy Computer architecture Deep learning Em-bedded devices Machine learning Malware detection Monitoring Multi-model architecture Performance evaluation Power demand Security Side channel analysis Software Speech recognition Transformers |
title | Two's Complement: Monitoring Software Control Flow Using Both Power and Electromagnetic Side Channels |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T00%3A48%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Two's%20Complement:%20Monitoring%20Software%20Control%20Flow%20Using%20Both%20Power%20and%20Electromagnetic%20Side%20Channels&rft.btitle=Proceedings%20(Euromicro%20Conference%20on%20Digital%20Systems%20Design)&rft.au=Amar,%20Michael&rft.date=2024-08-28&rft.spage=218&rft.epage=226&rft.pages=218-226&rft.eissn=2771-2508&rft.coden=IEEPAD&rft_id=info:doi/10.1109/DSD64264.2024.00037&rft.eisbn=9798350380385&rft_dat=%3Cieee_CHZPO%3E10741719%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-ieee_primary_107417193%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10741719&rfr_iscdi=true |