Learning Private Representations through Entropy-based Adversarial Training Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.10194

How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we introduce a variant of entropy - focal entropy, which mitigates the potential information leakage of the existing entropy-based approaches. We showcase feasibility on multiple benchmarks. The results suggest high target utility at moderate privacy leakage.

Related Topics

Learning Theory (Education)

My Own Private Idaho

Public–Private Partnership

Private Military Company

Attention (Machine Learning)

Private Eyes (Tv Series)

Private University

Learning

Private Dancer

Decision Tree Learning

Private Benjamin (1980 Film)

Private Browsing

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.10194
PDF: https://arxiv.org/pdf/2507.10194
OA Status: green
OpenAlex ID: https://openalex.org/W4414739196

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414739196

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.10194

Digital Object Identifier
Title: Learning Private Representations through Entropy-based Adversarial Training

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-14

Full publication date if available
Authors: Tassilo Klein, Moin Nabi

List of authors in order
Landing page: https://arxiv.org/abs/2507.10194

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.10194

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2507.10194

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4414739196
doi	https://doi.org/10.48550/arxiv.2507.10194
ids.doi	https://doi.org/10.48550/arxiv.2507.10194
ids.openalex	https://openalex.org/W4414739196
fwci
type	preprint
title	Learning Private Representations through Entropy-based Adversarial Training
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11689
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9951000213623047
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Adversarial Robustness in Machine Learning
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.10194
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2507.10194
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2507.10194
locations[1].id	doi:10.48550/arxiv.2507.10194
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2507.10194
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5023876634
authorships[0].author.orcid	https://orcid.org/0000-0002-0631-2940
authorships[0].author.display_name	Tassilo Klein
authorships[0].author_position	first
authorships[0].raw_author_name	Klein, Tassilo
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5001459748
authorships[1].author.orcid	https://orcid.org/0000-0001-7559-9888
authorships[1].author.display_name	Moin Nabi
authorships[1].author_position	last
authorships[1].raw_author_name	Nabi, Moin
authorships[1].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2507.10194
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Learning Private Representations through Entropy-based Adversarial Training
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11689
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9951000213623047
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Adversarial Robustness in Machine Learning
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.10194
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2507.10194
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2507.10194
primary_location.id	pmh:oai:arXiv.org:2507.10194
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2507.10194
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2507.10194
publication_date	2025-07-14
publication_year	2025
referenced_works_count	0
abstract_inverted_index.-	36
abstract_inverted_index.a	4, 32
abstract_inverted_index.We	14, 50
abstract_inverted_index.an	16
abstract_inverted_index.at	62
abstract_inverted_index.of	34, 45
abstract_inverted_index.on	53
abstract_inverted_index.we	2, 30
abstract_inverted_index.How	0
abstract_inverted_index.The	56
abstract_inverted_index.can	1
abstract_inverted_index.for	21
abstract_inverted_index.the	26, 41, 46
abstract_inverted_index.from	25
abstract_inverted_index.high	7, 59
abstract_inverted_index.user	12
abstract_inverted_index.with	6
abstract_inverted_index.focal	37
abstract_inverted_index.learn	3
abstract_inverted_index.power	9
abstract_inverted_index.which	39
abstract_inverted_index.while	10
abstract_inverted_index.method	20
abstract_inverted_index.target	60
abstract_inverted_index.content	24
abstract_inverted_index.entropy	35
abstract_inverted_index.leakage	44
abstract_inverted_index.learned	27
abstract_inverted_index.present	15
abstract_inverted_index.privacy	64
abstract_inverted_index.results	57
abstract_inverted_index.suggest	58
abstract_inverted_index.utility	61
abstract_inverted_index.variant	33
abstract_inverted_index.entropy,	38
abstract_inverted_index.existing	47
abstract_inverted_index.leakage.	65
abstract_inverted_index.learning	19
abstract_inverted_index.moderate	63
abstract_inverted_index.multiple	54
abstract_inverted_index.privacy?	13
abstract_inverted_index.showcase	51
abstract_inverted_index.introduce	31
abstract_inverted_index.mitigates	40
abstract_inverted_index.potential	42
abstract_inverted_index.sensitive	23
abstract_inverted_index.predictive	8
abstract_inverted_index.preserving	11
abstract_inverted_index.sanitizing	22
abstract_inverted_index.adversarial	17
abstract_inverted_index.approaches.	49
abstract_inverted_index.benchmarks.	55
abstract_inverted_index.feasibility	52
abstract_inverted_index.information	43
abstract_inverted_index.Specifically,	29
abstract_inverted_index.entropy-based	48
abstract_inverted_index.representation	5, 18
abstract_inverted_index.representation.	28
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile