ExpProof : Operationalizing Explanations for Confidential Models with ZKPs Article Swipe

PDF

Chhavi Yadav , Evan Monroe Laufer , Dan Boneh , Kamalika Chaudhuri ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.03773

In principle, explanations are intended as a way to increase trust in machine learning models and are often obligated by regulations. However, many circumstances where these are demanded are adversarial in nature, meaning the involved parties have misaligned interests and are incentivized to manipulate explanations for their purpose. As a result, explainability methods fail to be operational in such settings despite the demand \cite{bordt2022post}. In this paper, we take a step towards operationalizing explanations in adversarial scenarios with Zero-Knowledge Proofs (ZKPs), a cryptographic primitive. Specifically we explore ZKP-amenable versions of the popular explainability algorithm LIME and evaluate their performance on Neural Networks and Random Forests. Our code is publicly available at https://github.com/emlaufer/ExpProof.

Related Topics

Concepts

Operationalization Confidentiality Computer science Psychology Internet privacy Computer security Epistemology Philosophy

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2502.03773
PDF: https://arxiv.org/pdf/2502.03773
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4407244861

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4407244861

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2502.03773

Digital Object Identifier
Title: ExpProof : Operationalizing Explanations for Confidential Models with ZKPs

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-02-06

Full publication date if available
Authors: Chhavi Yadav, Evan Monroe Laufer, Dan Boneh, Kamalika Chaudhuri

List of authors in order
Landing page: https://arxiv.org/abs/2502.03773

Publisher landing page
PDF URL: https://arxiv.org/pdf/2502.03773

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/2502.03773

Direct OA link when available
Concepts: Operationalization, Confidentiality, Computer science, Psychology, Internet privacy, Computer security, Epistemology, Philosophy

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4407244861
doi	https://doi.org/10.48550/arxiv.2502.03773
ids.doi	https://doi.org/10.48550/arxiv.2502.03773
ids.openalex	https://openalex.org/W4407244861
fwci
type	preprint
title	ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11986
topics[0].field.id	https://openalex.org/fields/18
topics[0].field.display_name	Decision Sciences
topics[0].score	0.8461999893188477
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/1802
topics[0].subfield.display_name	Information Systems and Management
topics[0].display_name	Scientific Computing and Data Management
topics[1].id	https://openalex.org/T10927
topics[1].field.id	https://openalex.org/fields/33
topics[1].field.display_name	Social Sciences
topics[1].score	0.8378999829292297
topics[1].domain.id	https://openalex.org/domains/2
topics[1].domain.display_name	Social Sciences
topics[1].subfield.id	https://openalex.org/subfields/3312
topics[1].subfield.display_name	Sociology and Political Science
topics[1].display_name	Access Control and Trust
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C9354725
concepts[0].level	2
concepts[0].score	0.8832271099090576
concepts[0].wikidata	https://www.wikidata.org/wiki/Q286017
concepts[0].display_name	Operationalization
concepts[1].id	https://openalex.org/C71745522
concepts[1].level	2
concepts[1].score	0.6970424652099609
concepts[1].wikidata	https://www.wikidata.org/wiki/Q2476929
concepts[1].display_name	Confidentiality
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.38875898718833923
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C15744967
concepts[3].level	0
concepts[3].score	0.3433449864387512
concepts[3].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[3].display_name	Psychology
concepts[4].id	https://openalex.org/C108827166
concepts[4].level	1
concepts[4].score	0.3353906273841858
concepts[4].wikidata	https://www.wikidata.org/wiki/Q175975
concepts[4].display_name	Internet privacy
concepts[5].id	https://openalex.org/C38652104
concepts[5].level	1
concepts[5].score	0.23696374893188477
concepts[5].wikidata	https://www.wikidata.org/wiki/Q3510521
concepts[5].display_name	Computer security
concepts[6].id	https://openalex.org/C111472728
concepts[6].level	1
concepts[6].score	0.18190211057662964
concepts[6].wikidata	https://www.wikidata.org/wiki/Q9471
concepts[6].display_name	Epistemology
concepts[7].id	https://openalex.org/C138885662
concepts[7].level	0
concepts[7].score	0.11396557092666626
concepts[7].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[7].display_name	Philosophy
keywords[0].id	https://openalex.org/keywords/operationalization
keywords[0].score	0.8832271099090576
keywords[0].display_name	Operationalization
keywords[1].id	https://openalex.org/keywords/confidentiality
keywords[1].score	0.6970424652099609
keywords[1].display_name	Confidentiality
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.38875898718833923
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/psychology
keywords[3].score	0.3433449864387512
keywords[3].display_name	Psychology
keywords[4].id	https://openalex.org/keywords/internet-privacy
keywords[4].score	0.3353906273841858
keywords[4].display_name	Internet privacy
keywords[5].id	https://openalex.org/keywords/computer-security
keywords[5].score	0.23696374893188477
keywords[5].display_name	Computer security
keywords[6].id	https://openalex.org/keywords/epistemology
keywords[6].score	0.18190211057662964
keywords[6].display_name	Epistemology
keywords[7].id	https://openalex.org/keywords/philosophy
keywords[7].score	0.11396557092666626
keywords[7].display_name	Philosophy
language	en
locations[0].id	pmh:oai:arXiv.org:2502.03773
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/2502.03773
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/2502.03773
locations[1].id	doi:10.48550/arxiv.2502.03773
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.2502.03773
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5062539844
authorships[0].author.orcid
authorships[0].author.display_name	Chhavi Yadav
authorships[0].author_position	first
authorships[0].raw_author_name	Yadav, Chhavi
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5062862474
authorships[1].author.orcid
authorships[1].author.display_name	Evan Monroe Laufer
authorships[1].author_position	middle
authorships[1].raw_author_name	Laufer, Evan Monroe
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5027798962
authorships[2].author.orcid	https://orcid.org/0000-0003-0820-0421
authorships[2].author.display_name	Dan Boneh
authorships[2].author_position	middle
authorships[2].raw_author_name	Boneh, Dan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5010790447
authorships[3].author.orcid	https://orcid.org/0000-0001-9646-7710
authorships[3].author.display_name	Kamalika Chaudhuri
authorships[3].author_position	last
authorships[3].raw_author_name	Chaudhuri, Kamalika
authorships[3].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/2502.03773
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11986
primary_topic.field.id	https://openalex.org/fields/18
primary_topic.field.display_name	Decision Sciences
primary_topic.score	0.8461999893188477
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1802
primary_topic.subfield.display_name	Information Systems and Management
primary_topic.display_name	Scientific Computing and Data Management
related_works	https://openalex.org/W4391375266, https://openalex.org/W3183948672, https://openalex.org/W3173606202, https://openalex.org/W3110381201, https://openalex.org/W2948807893, https://openalex.org/W2899084033, https://openalex.org/W2778153218, https://openalex.org/W2748952813, https://openalex.org/W1531601525, https://openalex.org/W2112141997
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2502.03773
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/2502.03773
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/2502.03773
primary_location.id	pmh:oai:arXiv.org:2502.03773
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/2502.03773
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/2502.03773
publication_date	2025-02-06
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	6, 49, 69, 81
abstract_inverted_index.As	48
abstract_inverted_index.In	0, 64
abstract_inverted_index.as	5
abstract_inverted_index.at	110
abstract_inverted_index.be	55
abstract_inverted_index.by	19
abstract_inverted_index.in	11, 30, 57, 74
abstract_inverted_index.is	107
abstract_inverted_index.of	89
abstract_inverted_index.on	99
abstract_inverted_index.to	8, 42, 54
abstract_inverted_index.we	67, 85
abstract_inverted_index.Our	105
abstract_inverted_index.and	15, 39, 95, 102
abstract_inverted_index.are	3, 16, 26, 28, 40
abstract_inverted_index.for	45
abstract_inverted_index.the	33, 61, 90
abstract_inverted_index.way	7
abstract_inverted_index.LIME	94
abstract_inverted_index.code	106
abstract_inverted_index.fail	53
abstract_inverted_index.have	36
abstract_inverted_index.many	22
abstract_inverted_index.step	70
abstract_inverted_index.such	58
abstract_inverted_index.take	68
abstract_inverted_index.this	65
abstract_inverted_index.with	77
abstract_inverted_index.often	17
abstract_inverted_index.their	46, 97
abstract_inverted_index.these	25
abstract_inverted_index.trust	10
abstract_inverted_index.where	24
abstract_inverted_index.Neural	100
abstract_inverted_index.Proofs	79
abstract_inverted_index.Random	103
abstract_inverted_index.demand	62
abstract_inverted_index.models	14
abstract_inverted_index.paper,	66
abstract_inverted_index.(ZKPs),	80
abstract_inverted_index.despite	60
abstract_inverted_index.explore	86
abstract_inverted_index.machine	12
abstract_inverted_index.meaning	32
abstract_inverted_index.methods	52
abstract_inverted_index.nature,	31
abstract_inverted_index.parties	35
abstract_inverted_index.popular	91
abstract_inverted_index.result,	50
abstract_inverted_index.towards	71
abstract_inverted_index.Forests.	104
abstract_inverted_index.However,	21
abstract_inverted_index.Networks	101
abstract_inverted_index.demanded	27
abstract_inverted_index.evaluate	96
abstract_inverted_index.increase	9
abstract_inverted_index.intended	4
abstract_inverted_index.involved	34
abstract_inverted_index.learning	13
abstract_inverted_index.publicly	108
abstract_inverted_index.purpose.	47
abstract_inverted_index.settings	59
abstract_inverted_index.versions	88
abstract_inverted_index.algorithm	93
abstract_inverted_index.available	109
abstract_inverted_index.interests	38
abstract_inverted_index.obligated	18
abstract_inverted_index.scenarios	76
abstract_inverted_index.manipulate	43
abstract_inverted_index.misaligned	37
abstract_inverted_index.primitive.	83
abstract_inverted_index.principle,	1
abstract_inverted_index.adversarial	29, 75
abstract_inverted_index.operational	56
abstract_inverted_index.performance	98
abstract_inverted_index.Specifically	84
abstract_inverted_index.ZKP-amenable	87
abstract_inverted_index.explanations	2, 44, 73
abstract_inverted_index.incentivized	41
abstract_inverted_index.regulations.	20
abstract_inverted_index.circumstances	23
abstract_inverted_index.cryptographic	82
abstract_inverted_index.Zero-Knowledge	78
abstract_inverted_index.explainability	51, 92
abstract_inverted_index.operationalizing	72
abstract_inverted_index.\cite{bordt2022post}.	63
abstract_inverted_index.https://github.com/emlaufer/ExpProof.	111
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile