Disentangled Information Bottleneck Guided Privacy-Protective Joint Source and Channel Coding for Image Transmission

Joint source and channel coding (JSCC) has attracted increasing attention in semantic communications. However, JSCC is vulnerable to privacy issues due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-pro...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on communications Ročník 72; číslo 11; s. 6992 - 7005
Hlavní autoři:	Sun, Lunan, Yang, Yang, Chen, Mingzhe, Guo, Caili
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.11.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Coding Design optimization Distortion Eavesdropping Encryption Image communication Image quality Image reconstruction Image transmission information bottleneck Joint source and channel coding Maximum entropy Neural networks Noise measurement Privacy privacy protection Protection semantic communication
ISSN:	0090-6778, 1558-0857
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Joint source and channel coding (JSCC) has attracted increasing attention in semantic communications. However, JSCC is vulnerable to privacy issues due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-protective JSCC (DPJSCC) for image transmission, which aims at protecting private information and achieving superior image transmission performance. In particular, we propose a disentangled information bottleneck objective to compress the private information in public subcodewords and improve the reconstruction quality simultaneously. To optimize JSCC neural networks using the proposed objective, we derive a differentiable estimation based on variational approximation and the density-ratio trick. Additionally, we design a password-based privacy-protective algorithm that encrypts the private subcodewords, achieving joint optimization with JSCC neural networks. The proposed algorithm involves an encryptor for encrypting private information and a decryptor for recovering it at the legitimate receiver. A loss function is derived based on the maximum entropy principle for jointly training the encryptor, decryptor, and JSCC decoder to maximize eavesdropping uncertainty and improve reconstruction quality. Experimental results show that DPJSCC reduces eavesdropping accuracy on private information by up to 18% and decreases inference time by 10%.
AbstractList	Joint source and channel coding (JSCC) has attracted increasing attention in semantic communications. However, JSCC is vulnerable to privacy issues due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-protective JSCC (DPJSCC) for image transmission, which aims at protecting private information and achieving superior image transmission performance. In particular, we propose a disentangled information bottleneck objective to compress the private information in public subcodewords and improve the reconstruction quality simultaneously. To optimize JSCC neural networks using the proposed objective, we derive a differentiable estimation based on variational approximation and the density-ratio trick. Additionally, we design a password-based privacy-protective algorithm that encrypts the private subcodewords, achieving joint optimization with JSCC neural networks. The proposed algorithm involves an encryptor for encrypting private information and a decryptor for recovering it at the legitimate receiver. A loss function is derived based on the maximum entropy principle for jointly training the encryptor, decryptor, and JSCC decoder to maximize eavesdropping uncertainty and improve reconstruction quality. Experimental results show that DPJSCC reduces eavesdropping accuracy on private information by up to 18% and decreases inference time by 10%.
Author	Sun, Lunan Guo, Caili Chen, Mingzhe Yang, Yang
Author_xml	– sequence: 1 givenname: Lunan orcidid: 0009-0009-6628-9314 surname: Sun fullname: Sun, Lunan email: sunlunan@bupt.edu.cn organization: Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 2 givenname: Yang orcidid: 0000-0002-1353-0890 surname: Yang fullname: Yang, Yang email: yangyang01@bupt.edu.cn organization: Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 3 givenname: Mingzhe orcidid: 0000-0003-2570-703X surname: Chen fullname: Chen, Mingzhe email: mingzhe.chen@miami.edu organization: Department of Electrical and Computer Engineering and the Institute for Data Science and Computing, University of Miami, Coral Gables, FL, USA – sequence: 4 givenname: Caili orcidid: 0000-0001-8892-4520 surname: Guo fullname: Guo, Caili email: guocaili@bupt.edu.cn organization: Beijing Laboratory of Advanced Information Networks, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China
BookMark	eNp9kM1OLCEQhYnRxPHnBYwLEtc9F5qmgaW2P3duNJo4rjsMXYxoDygwJr696Li4ceGqFnW-U5VvD2374AGhI0qmlBL1Z97d3txMa1I3U9aQlkm6hSaUc1kRycU2mhCiSNUKIXfRXkpPhJCGMDZB-dwl8Fn75QgDnnkb4kpnFzw-CzmP4ME846u1G8r2Lro3bd6ruxgymOzeAP8Lzmd8H9bRANZ-wN2j9h5G3IXB-SUudXi20kvA86h9WrmUSvcB2rF6THD4PffRw-XFvPtbXd9ezbrT68rUqs2VbcEKOwizkIqrujFS15wy0C0ozfUgFnphaGskbQyvhVV2wYllTV2UDJxKto9ONr0vMbyuIeX-qXzqy8meUUYUK0lVUvUmZWJIKYLtX6Jb6fjeU9J_2u2_7PafdvtvuwWSPyDj8pe4HLUbf0ePN6gDgP9u8UYQ0bAPFDSL6A
CODEN	IECMBT
CitedBy_id	crossref_primary_10_1109_JSAC_2025_3559121
Cites_doi	10.1109/CVPR.2016.90 10.1109/ICASSP40776.2020.9053216 10.1109/COMST.2022.3223224 10.1162/neco.2006.18.7.1527 10.1109/TWC.2023.3269444 10.1109/JSAIT.2021.3062755 10.1109/JSAIT.2020.2987203 10.1109/CVPR.2017.463 10.1007/0-387-23483-7_94 10.1155/2008/179290 10.1109/TCOMM.2022.3222874 10.1109/ICPR.2018.8546038 10.1109/TWC.2004.837271 10.1109/CVPR.2019.00269 10.1109/JSAC.2020.2986665 10.1109/TCOMM.2005.844936 10.1109/5.726791 10.1109/MIE.2022.3174331 10.1145/2810103.2813687 10.1002/j.1538-7305.1948.tb01338.x 10.1109/TIT.2010.2068870 10.1109/TIT.2003.810631 10.1016/j.neucom.2019.11.041 10.1109/TCSVT.2021.3082521 10.1109/TCCN.2023.3306851 10.1007/978-3-7091-2945-6 10.1109/TCCN.2019.2919300 10.1109/18.485714 10.1609/aaai.v35i10.17120 10.1109/JSAC.2023.3288238 10.1109/JSAC.2021.3118346 10.1609/aaai.v34i04.6041 10.1109/TIT.1962.1057683 10.1109/TCOMM.2022.3180997 10.1109/ICASSP43922.2022.9747068 10.1109/LCOMM.2020.2994884 10.1016/S1353-4858(10)70006-4 10.1109/CVPR.2018.00087 10.1109/icc45041.2023.10278612 10.1109/TCOMM.2017.2704586 10.1109/ICCV48922.2021.00859 10.1109/TCOMM.2004.840664
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TCOMM.2024.3406381
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0857
EndPage	7005
ExternalDocumentID	10_1109_TCOMM_2024_3406381 10547074
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62371070 funderid: 10.13039/501100001809 – fundername: Fundamental Research Funds for the Central Universities grantid: 2021XD-A01-1 funderid: 10.13039/501100012226 – fundername: Beiiing Natural Science Foundation grantid: L222043
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD HZ~ H~9 IAAWW IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 ZCA ZCG AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c296t-f6ef7fd7cb895924c8a2513ea6e9a5ad7babc16c814c527f9fb50f342110d5183
IEDL.DBID	RIE
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001361615600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0090-6778
IngestDate	Mon Jun 30 10:18:37 EDT 2025 Tue Nov 18 22:23:12 EST 2025 Sat Nov 29 04:08:28 EST 2025 Wed Aug 27 03:06:46 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	11
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c296t-f6ef7fd7cb895924c8a2513ea6e9a5ad7babc16c814c527f9fb50f342110d5183
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-8892-4520 0000-0002-1353-0890 0009-0009-6628-9314 0000-0003-2570-703X
PQID	3130932119
PQPubID	85472
PageCount	14
ParticipantIDs	proquest_journals_3130932119 crossref_primary_10_1109_TCOMM_2024_3406381 ieee_primary_10547074 crossref_citationtrail_10_1109_TCOMM_2024_3406381
PublicationCentury	2000
PublicationDate	2024-11-01
PublicationDateYYYYMMDD	2024-11-01
PublicationDate_xml	– month: 11 year: 2024 text: 2024-11-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on communications
PublicationTitleAbbrev	TCOMM
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 Van der Maaten (ref50) 2008; 9 ref14 ref52 ref11 ref10 ref17 ref16 ref19 ref51 Kim (ref37) ref45 Bellard (ref46) 2018 ref47 ref42 ref41 ref44 ref43 Choi (ref15); 97 Tishby (ref30) 2000 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref31 ref33 ref32 Alemi (ref36) 2016 Chen (ref38) ref1 ref39 Chafii (ref2) 2022 ref24 ref23 Qin (ref18) 2021 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 Simonyan (ref48) 2014
References_xml	– ident: ref49 doi: 10.1109/CVPR.2016.90 – ident: ref25 doi: 10.1109/ICASSP40776.2020.9053216 – start-page: 2649 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref37 article-title: Disentangling by factorising – ident: ref17 doi: 10.1109/COMST.2022.3223224 – ident: ref42 doi: 10.1162/neco.2006.18.7.1527 – ident: ref19 doi: 10.1109/TWC.2023.3269444 – ident: ref29 doi: 10.1109/JSAIT.2021.3062755 – ident: ref12 doi: 10.1109/JSAIT.2020.2987203 – ident: ref44 doi: 10.1109/CVPR.2017.463 – ident: ref33 doi: 10.1007/0-387-23483-7_94 – ident: ref24 doi: 10.1155/2008/179290 – ident: ref10 doi: 10.1109/TCOMM.2022.3222874 – ident: ref45 doi: 10.1109/ICPR.2018.8546038 – ident: ref52 doi: 10.1109/TWC.2004.837271 – ident: ref27 doi: 10.1109/CVPR.2019.00269 – ident: ref21 doi: 10.1109/JSAC.2020.2986665 – start-page: 2610 volume-title: Proc. Adv. Neural Inform. Process. Syst. ident: ref38 article-title: Isolating sources of disentanglement in variational autoencoders – ident: ref4 doi: 10.1109/TCOMM.2005.844936 – volume: 9 start-page: 2579 issue: 11 year: 2008 ident: ref50 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – ident: ref43 doi: 10.1109/5.726791 – ident: ref8 doi: 10.1109/MIE.2022.3174331 – ident: ref20 doi: 10.1145/2810103.2813687 – ident: ref1 doi: 10.1002/j.1538-7305.1948.tb01338.x – year: 2022 ident: ref2 article-title: Twelve scientific challenges for 6G: Rethinking the foundations of communications theory publication-title: arXiv:2207.01843 – ident: ref40 doi: 10.1109/TIT.2010.2068870 – year: 2000 ident: ref30 article-title: The information bottleneck method publication-title: arXiv:physics/0004057 – year: 2014 ident: ref48 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv:1409.1556 – ident: ref7 doi: 10.1109/TIT.2003.810631 – ident: ref28 doi: 10.1016/j.neucom.2019.11.041 – ident: ref14 doi: 10.1109/TCSVT.2021.3082521 – ident: ref22 doi: 10.1109/TCCN.2023.3306851 – ident: ref6 doi: 10.1007/978-3-7091-2945-6 – volume-title: BPG Image Format year: 2018 ident: ref46 – ident: ref11 doi: 10.1109/TCCN.2019.2919300 – ident: ref51 doi: 10.1109/18.485714 – ident: ref31 doi: 10.1609/aaai.v35i10.17120 – ident: ref13 doi: 10.1109/JSAC.2023.3288238 – ident: ref3 doi: 10.1109/JSAC.2021.3118346 – volume: 97 start-page: 1182 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref15 article-title: Neural joint source-channel coding – ident: ref16 doi: 10.1609/aaai.v34i04.6041 – ident: ref47 doi: 10.1109/TIT.1962.1057683 – ident: ref9 doi: 10.1109/TCOMM.2022.3180997 – ident: ref26 doi: 10.1109/ICASSP43922.2022.9747068 – ident: ref35 doi: 10.1109/LCOMM.2020.2994884 – ident: ref32 doi: 10.1016/S1353-4858(10)70006-4 – ident: ref41 doi: 10.1109/CVPR.2018.00087 – ident: ref23 doi: 10.1109/icc45041.2023.10278612 – ident: ref34 doi: 10.1109/TCOMM.2017.2704586 – ident: ref39 doi: 10.1109/ICCV48922.2021.00859 – year: 2016 ident: ref36 article-title: Deep variational information bottleneck publication-title: arXiv:1612.00410 – ident: ref5 doi: 10.1109/TCOMM.2004.840664 – year: 2021 ident: ref18 article-title: Semantic communications: Principles and challenges publication-title: arXiv:2201.01389
SSID	ssj0004033
Score	2.4909053
Snippet	Joint source and channel coding (JSCC) has attracted increasing attention in semantic communications. However, JSCC is vulnerable to privacy issues due to the...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	6992
SubjectTerms	Algorithms Coding Design optimization Distortion Eavesdropping Encryption Image communication Image quality Image reconstruction Image transmission information bottleneck Joint source and channel coding Maximum entropy Neural networks Noise measurement Privacy privacy protection Protection semantic communication
Title	Disentangled Information Bottleneck Guided Privacy-Protective Joint Source and Channel Coding for Image Transmission
URI	https://ieeexplore.ieee.org/document/10547074 https://www.proquest.com/docview/3130932119
Volume	72
WOSCitedRecordID	wos001361615600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0857 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004033 issn: 0090-6778 databaseCode: RIE dateStart: 19720101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTxsxELZK1AM9tJSHCATkAze0afblx5GGR1sBjdQgcVut7TFaEXarZBOJf4_Hu4EgVKTeVlrbWu1nz3g8_r4h5CixKTdcsMCA1QEmZgJlpQoiEEyCFEwZL5l_ya-vxe2tHLVkdc-FAQB_-Qz6-Ohz-abSczwqcys8TbjzeWtkjXPWkLVeSJCDuJWcxPvsXCwZMgP5bTz8fXXlYsEo6ccJ-ujwlRfyZVXe2GLvYM6__OenbZDP7U6SnjTQfyUfoNwkn1b0BbdIfVp4blF5NwFDW-YRIkG_V6hdXIK-pxfzwri3o2mxyPVjMGqEG5wRpL-qoqzpH3-8T_PSUKQilDChwwo9HnXD0Z8PziBR7_HcjMGjt21yc342Hv4I2jILgY4kqwPLwHJruFZCpi4c0yJ3m54YcgYyT3PDVa50yLQIE51G3Eqr0oGNEwwdTepMwg7plFUJu4SqGJTwomgSEsOMFEYCBxfUqTA3ke6ScPnbM91qkGMpjEnmY5GBzDxUGUKVtVB1yfFzn7-NAse7rbcRnJWWDS5d0lvCm7WrdJbFIeaBUeNu7x_d9sk6jt6QD3ukU0_ncEA-6kVdzKaHfgI-AX1Y2dA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VFgk4UB6LWCjgAzeUkocT20dY6AN2l5VYpN6i2B5XUZcEbbOV-Pd4nCwUIZC4RYqdRPnsGc-Mv88AL7nLhRWyiCw6E1FhJtJO6ShFWShUstA2SOZPxXwuz87UYiCrBy4MIobNZ3hIl6GWb1uzoVSZn-E5F97n3YC9nPM07ulav2iQcTaITtKOdiG3HJlYvV5OPs1mPhpM-WHGyUsnv_mhcLDKH9Y4uJij_f_8uHtwd1hLsjc9-PdhB5sHcOeawuBD6N7VgV3UnK_QsoF7RFiwty2pFzdoLtjxprb-7mJdX1Xme7TopRu8GWQf2rrp2OeQ4GdVYxmRERpcsUlLPo_5x7HTr94kseDz_Jih5NsIvhy9X05OouGghcikqugiV6ATzgqjpcp9QGZk5Zc9GVYFqiqvrNCVNklhZMJNngqnnM5jl3EKHm3ujcIj2G3aBh8D0xlqGWTRFHJbWCWtQoE-rNNJZVMzhmT720szqJDTYRirMkQjsSoDVCVBVQ5QjeHVzz7feg2Of7YeETjXWva4jOFgC285zNPLMkuoEkwqd0_-0u0F3DpZzqbl9HT-8Sncpjf1VMQD2O3WG3wGN81VV1-un4fB-AP3_t0X
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Disentangled+Information+Bottleneck+Guided+Privacy-Protective+Joint+Source+and+Channel+Coding+for+Image+Transmission&rft.jtitle=IEEE+transactions+on+communications&rft.au=Sun%2C+Lunan&rft.au=Yang%2C+Yang&rft.au=Chen%2C+Mingzhe&rft.au=Guo%2C+Caili&rft.date=2024-11-01&rft.pub=IEEE&rft.issn=0090-6778&rft.volume=72&rft.issue=11&rft.spage=6992&rft.epage=7005&rft_id=info:doi/10.1109%2FTCOMM.2024.3406381&rft.externalDocID=10547074
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon