Adversarial attacks in signature verification: a deep learning approach Article Swipe

View

Abhisek Hazra , Saroj Maity , Barnali Pal , Asok Bandyopadhyay ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.11591/csit.v5i3.p215-226

Handwritten signature recognition in forensic science is crucial for identity and document authentication. While serving as a legal representation of a person’s agreement or consent to the contents of a document, handwritten signatures de termine the authenticity of a document, identify forgeries, pinpoint the suspects and support other pieces of evidence like ink or document analysis. This work focuses on developing and evaluating a handwritten signature verification sys tem using a convolutional neural network (CNN) and emphasising the model’s efficacy using hand-crafted adversarial attacks. Initially, handwritten signatures have been collected from sixteen volunteers, each contributing ten samples, fol lowed by image normalization and augmentation to boost synthetic data samples and overcome the data scarcity. The proposed model achieved a testing accu racy of 91.35% using an 80:20 train-test split. Additionally, using the five-fold cross-validation, the model achieved a robust validation accuracy of nearly 98%. Finally, the introduction of manually constructed adversarial assaults on the sig nature images undermines the model’s accuracy, bringing the accuracy down to nearly 80%. This highlights the need to consider adversarial resilience while designing deep learning models for classification tasks. Exposing the model to real look-alike fake samples is critical while testing its robustness and refining the model using trial and error methods.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Adversarial system Signature (topology) Computer science Artificial intelligence Deep learning Computer security Mathematics Geometry

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.11591/csit.v5i3.p215-226
OA Status: diamond
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4403692998

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4403692998

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.11591/csit.v5i3.p215-226

Digital Object Identifier
Title: Adversarial attacks in signature verification: a deep learning approach

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-10-23

Full publication date if available
Authors: Abhisek Hazra, Saroj Maity, Barnali Pal, Asok Bandyopadhyay

List of authors in order
Landing page: https://doi.org/10.11591/csit.v5i3.p215-226

Publisher landing page
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://doi.org/10.11591/csit.v5i3.p215-226

Direct OA link when available
Concepts: Adversarial system, Signature (topology), Computer science, Artificial intelligence, Deep learning, Computer security, Mathematics, Geometry

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4403692998
doi	https://doi.org/10.11591/csit.v5i3.p215-226
ids.doi	https://doi.org/10.11591/csit.v5i3.p215-226
ids.openalex	https://openalex.org/W4403692998
fwci	0.53015756
type	article
title	Adversarial attacks in signature verification: a deep learning approach
biblio.issue	3
biblio.volume	5
biblio.last_page	226
biblio.first_page	215
topics[0].id	https://openalex.org/T10601
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.960099995136261
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Handwritten Text Recognition Techniques
topics[1].id	https://openalex.org/T10181
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9509999752044678
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Natural Language Processing Techniques
topics[2].id	https://openalex.org/T10028
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.942300021648407
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Topic Modeling
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C37736160
concepts[0].level	2
concepts[0].score	0.8002511858940125
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1801315
concepts[0].display_name	Adversarial system
concepts[1].id	https://openalex.org/C2779696439
concepts[1].level	2
concepts[1].score	0.7475794553756714
concepts[1].wikidata	https://www.wikidata.org/wiki/Q7512811
concepts[1].display_name	Signature (topology)
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.6139382123947144
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.5616691708564758
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C108583219
concepts[4].level	2
concepts[4].score	0.452075719833374
concepts[4].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[4].display_name	Deep learning
concepts[5].id	https://openalex.org/C38652104
concepts[5].level	1
concepts[5].score	0.3634401559829712
concepts[5].wikidata	https://www.wikidata.org/wiki/Q3510521
concepts[5].display_name	Computer security
concepts[6].id	https://openalex.org/C33923547
concepts[6].level	0
concepts[6].score	0.12803366780281067
concepts[6].wikidata	https://www.wikidata.org/wiki/Q395
concepts[6].display_name	Mathematics
concepts[7].id	https://openalex.org/C2524010
concepts[7].level	1
concepts[7].score	0.0
concepts[7].wikidata	https://www.wikidata.org/wiki/Q8087
concepts[7].display_name	Geometry
keywords[0].id	https://openalex.org/keywords/adversarial-system
keywords[0].score	0.8002511858940125
keywords[0].display_name	Adversarial system
keywords[1].id	https://openalex.org/keywords/signature
keywords[1].score	0.7475794553756714
keywords[1].display_name	Signature (topology)
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.6139382123947144
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.5616691708564758
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/deep-learning
keywords[4].score	0.452075719833374
keywords[4].display_name	Deep learning
keywords[5].id	https://openalex.org/keywords/computer-security
keywords[5].score	0.3634401559829712
keywords[5].display_name	Computer security
keywords[6].id	https://openalex.org/keywords/mathematics
keywords[6].score	0.12803366780281067
keywords[6].display_name	Mathematics
language	en
locations[0].id	doi:10.11591/csit.v5i3.p215-226
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210218571
locations[0].source.issn	2722-3221, 2722-323X
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	2722-3221
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	Computer Science and Information Technologies
locations[0].source.host_organization	https://openalex.org/P4310315009
locations[0].source.host_organization_name	Institute of Advanced Engineering and Science (IAES)
locations[0].source.host_organization_lineage	https://openalex.org/P4310315009
locations[0].source.host_organization_lineage_names	Institute of Advanced Engineering and Science (IAES)
locations[0].license
locations[0].pdf_url
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Computer Science and Information Technologies
locations[0].landing_page_url	https://doi.org/10.11591/csit.v5i3.p215-226
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5043636415
authorships[0].author.orcid	https://orcid.org/0000-0003-0141-4339
authorships[0].author.display_name	Abhisek Hazra
authorships[0].author_position	first
authorships[0].raw_author_name	Abhisek Hazra
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5072408183
authorships[1].author.orcid	https://orcid.org/0009-0003-3404-9515
authorships[1].author.display_name	Saroj Maity
authorships[1].author_position	middle
authorships[1].raw_author_name	Shuvajit Maity
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5056243655
authorships[2].author.orcid	https://orcid.org/0000-0001-7415-1176
authorships[2].author.display_name	Barnali Pal
authorships[2].author_position	middle
authorships[2].raw_author_name	Barnali Pal
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5007675306
authorships[3].author.orcid	https://orcid.org/0000-0002-5519-8670
authorships[3].author.display_name	Asok Bandyopadhyay
authorships[3].author_position	last
authorships[3].raw_author_name	Asok Bandyopadhyay
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://doi.org/10.11591/csit.v5i3.p215-226
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Adversarial attacks in signature verification: a deep learning approach
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T10601
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.960099995136261
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Handwritten Text Recognition Techniques
related_works	https://openalex.org/W2731899572, https://openalex.org/W3215138031, https://openalex.org/W4321369474, https://openalex.org/W3009238340, https://openalex.org/W4360585206, https://openalex.org/W4285208911, https://openalex.org/W3082895349, https://openalex.org/W4213079790, https://openalex.org/W2248239756, https://openalex.org/W4323565446
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	1
best_oa_location.id	doi:10.11591/csit.v5i3.p215-226
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210218571
best_oa_location.source.issn	2722-3221, 2722-323X
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	2722-3221
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	Computer Science and Information Technologies
best_oa_location.source.host_organization	https://openalex.org/P4310315009
best_oa_location.source.host_organization_name	Institute of Advanced Engineering and Science (IAES)
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310315009
best_oa_location.source.host_organization_lineage_names	Institute of Advanced Engineering and Science (IAES)
best_oa_location.license
best_oa_location.pdf_url
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Computer Science and Information Technologies
best_oa_location.landing_page_url	https://doi.org/10.11591/csit.v5i3.p215-226
primary_location.id	doi:10.11591/csit.v5i3.p215-226
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210218571
primary_location.source.issn	2722-3221, 2722-323X
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	2722-3221
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	Computer Science and Information Technologies
primary_location.source.host_organization	https://openalex.org/P4310315009
primary_location.source.host_organization_name	Institute of Advanced Engineering and Science (IAES)
primary_location.source.host_organization_lineage	https://openalex.org/P4310315009
primary_location.source.host_organization_lineage_names	Institute of Advanced Engineering and Science (IAES)
primary_location.license
primary_location.pdf_url
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Computer Science and Information Technologies
primary_location.landing_page_url	https://doi.org/10.11591/csit.v5i3.p215-226
publication_date	2024-10-23
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	16, 20, 29, 38, 63, 70, 118, 137
abstract_inverted_index.an	125
abstract_inverted_index.as	15
abstract_inverted_index.by	99
abstract_inverted_index.de	33
abstract_inverted_index.in	3
abstract_inverted_index.is	6, 192
abstract_inverted_index.of	19, 28, 37, 49, 122, 141, 147
abstract_inverted_index.on	59, 152
abstract_inverted_index.or	23, 53
abstract_inverted_index.to	25, 104, 165, 172, 187
abstract_inverted_index.The	114
abstract_inverted_index.and	10, 45, 61, 75, 102, 109, 198, 204
abstract_inverted_index.fol	97
abstract_inverted_index.for	8, 181
abstract_inverted_index.ink	52
abstract_inverted_index.its	196
abstract_inverted_index.sig	154
abstract_inverted_index.sys	67
abstract_inverted_index.tem	68
abstract_inverted_index.ten	95
abstract_inverted_index.the	26, 35, 43, 77, 111, 131, 134, 145, 153, 158, 162, 170, 185, 200
abstract_inverted_index.80%.	167
abstract_inverted_index.98%.	143
abstract_inverted_index.This	56, 168
abstract_inverted_index.accu	120
abstract_inverted_index.been	88
abstract_inverted_index.data	107, 112
abstract_inverted_index.deep	178
abstract_inverted_index.down	164
abstract_inverted_index.each	93
abstract_inverted_index.fake	190
abstract_inverted_index.from	90
abstract_inverted_index.have	87
abstract_inverted_index.like	51
abstract_inverted_index.need	171
abstract_inverted_index.racy	121
abstract_inverted_index.real	188
abstract_inverted_index.work	57
abstract_inverted_index.(CNN)	74
abstract_inverted_index.80:20	126
abstract_inverted_index.While	13
abstract_inverted_index.boost	105
abstract_inverted_index.error	205
abstract_inverted_index.image	100
abstract_inverted_index.legal	17
abstract_inverted_index.lowed	98
abstract_inverted_index.model	116, 135, 186, 201
abstract_inverted_index.other	47
abstract_inverted_index.trial	203
abstract_inverted_index.using	69, 80, 124, 130, 202
abstract_inverted_index.while	176, 194
abstract_inverted_index.91.35%	123
abstract_inverted_index.images	156
abstract_inverted_index.models	180
abstract_inverted_index.nature	155
abstract_inverted_index.nearly	142, 166
abstract_inverted_index.neural	72
abstract_inverted_index.pieces	48
abstract_inverted_index.robust	138
abstract_inverted_index.split.	128
abstract_inverted_index.tasks.	183
abstract_inverted_index.consent	24
abstract_inverted_index.crucial	7
abstract_inverted_index.focuses	58
abstract_inverted_index.network	73
abstract_inverted_index.samples	108, 191
abstract_inverted_index.science	5
abstract_inverted_index.serving	14
abstract_inverted_index.sixteen	91
abstract_inverted_index.support	46
abstract_inverted_index.termine	34
abstract_inverted_index.testing	119, 195
abstract_inverted_index.Exposing	184
abstract_inverted_index.Finally,	144
abstract_inverted_index.accuracy	140, 163
abstract_inverted_index.achieved	117, 136
abstract_inverted_index.assaults	151
abstract_inverted_index.attacks.	83
abstract_inverted_index.bringing	161
abstract_inverted_index.consider	173
abstract_inverted_index.contents	27
abstract_inverted_index.critical	193
abstract_inverted_index.document	11, 54
abstract_inverted_index.efficacy	79
abstract_inverted_index.evidence	50
abstract_inverted_index.forensic	4
abstract_inverted_index.identify	40
abstract_inverted_index.identity	9
abstract_inverted_index.learning	179
abstract_inverted_index.manually	148
abstract_inverted_index.methods.	206
abstract_inverted_index.overcome	110
abstract_inverted_index.pinpoint	42
abstract_inverted_index.proposed	115
abstract_inverted_index.refining	199
abstract_inverted_index.samples,	96
abstract_inverted_index.suspects	44
abstract_inverted_index.accuracy,	160
abstract_inverted_index.agreement	22
abstract_inverted_index.analysis.	55
abstract_inverted_index.collected	89
abstract_inverted_index.designing	177
abstract_inverted_index.document,	30, 39
abstract_inverted_index.five-fold	132
abstract_inverted_index.model’s	78, 159
abstract_inverted_index.scarcity.	113
abstract_inverted_index.signature	1, 65
abstract_inverted_index.synthetic	106
abstract_inverted_index.Initially,	84
abstract_inverted_index.developing	60
abstract_inverted_index.evaluating	62
abstract_inverted_index.forgeries,	41
abstract_inverted_index.highlights	169
abstract_inverted_index.look-alike	189
abstract_inverted_index.person’s	21
abstract_inverted_index.resilience	175
abstract_inverted_index.robustness	197
abstract_inverted_index.signatures	32, 86
abstract_inverted_index.train-test	127
abstract_inverted_index.undermines	157
abstract_inverted_index.validation	139
abstract_inverted_index.Handwritten	0
abstract_inverted_index.adversarial	82, 150, 174
abstract_inverted_index.constructed	149
abstract_inverted_index.emphasising	76
abstract_inverted_index.handwritten	31, 64, 85
abstract_inverted_index.recognition	2
abstract_inverted_index.volunteers,	92
abstract_inverted_index.augmentation	103
abstract_inverted_index.authenticity	36
abstract_inverted_index.contributing	94
abstract_inverted_index.hand-crafted	81
abstract_inverted_index.introduction	146
abstract_inverted_index.verification	66
abstract_inverted_index.Additionally,	129
abstract_inverted_index.convolutional	71
abstract_inverted_index.normalization	101
abstract_inverted_index.classification	182
abstract_inverted_index.representation	18
abstract_inverted_index.authentication.	12
abstract_inverted_index.cross-validation,	133
cited_by_percentile_year.max	95
cited_by_percentile_year.min	91
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile.value	0.61981072
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False