@inproceedings{fang-etal-2026-sparkshield,
title = "{S}park{S}hield at {A}r{A}-{DF} 2026: Robust {A}rabic Speech Deepfake Detection via Realistic Audio Augmentation and Multi-Scale {XLS}-{R} Score Fusion",
author = "Fang, Xin and
Xu, Haitao and
Xie, Zhipeng and
Gao, Tian and
Cao, Junqin and
Fan, Cunhang and
Wu, Minghui",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.190/",
pages = "1486--1490",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents the SparkShield system submitted to ArA-DF 2026 Track 2, which focuses on robust Arabic speech deepfake detection under realistic acoustic degradations. To improve robustness, we apply a comprehensive augmentation pipeline involving background noise, reverberation, codec compression, reencoding, and volume perturbation. Our system consists of three parallel subsystems using XLS-R models with 300M, 1B, and 2B parameters as front-end feature extractors. Each subsystem employs learnable layer-wise feature fusion, followed by a Multi-kernel gated Convolution (MultiConv) module and Multi-Head Attention Pooling (MHAP) for utterance-level spoof detection. The output logits of the three independently trained subsystems are finally fused. The proposed system achieves an EER of 0.6575{\%} on the evaluation set and ranks first in ArA-DF 2026 Track 2."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2026-sparkshield">
<titleInfo>
<title>SparkShield at ArA-DF 2026: Robust Arabic Speech Deepfake Detection via Realistic Audio Augmentation and Multi-Scale XLS-R Score Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junqin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunhang</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>This paper presents the SparkShield system submitted to ArA-DF 2026 Track 2, which focuses on robust Arabic speech deepfake detection under realistic acoustic degradations. To improve robustness, we apply a comprehensive augmentation pipeline involving background noise, reverberation, codec compression, reencoding, and volume perturbation. Our system consists of three parallel subsystems using XLS-R models with 300M, 1B, and 2B parameters as front-end feature extractors. Each subsystem employs learnable layer-wise feature fusion, followed by a Multi-kernel gated Convolution (MultiConv) module and Multi-Head Attention Pooling (MHAP) for utterance-level spoof detection. The output logits of the three independently trained subsystems are finally fused. The proposed system achieves an EER of 0.6575% on the evaluation set and ranks first in ArA-DF 2026 Track 2.</abstract>
<identifier type="citekey">fang-etal-2026-sparkshield</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.190/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1486</start>
<end>1490</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SparkShield at ArA-DF 2026: Robust Arabic Speech Deepfake Detection via Realistic Audio Augmentation and Multi-Scale XLS-R Score Fusion
%A Fang, Xin
%A Xu, Haitao
%A Xie, Zhipeng
%A Gao, Tian
%A Cao, Junqin
%A Fan, Cunhang
%A Wu, Minghui
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F fang-etal-2026-sparkshield
%X This paper presents the SparkShield system submitted to ArA-DF 2026 Track 2, which focuses on robust Arabic speech deepfake detection under realistic acoustic degradations. To improve robustness, we apply a comprehensive augmentation pipeline involving background noise, reverberation, codec compression, reencoding, and volume perturbation. Our system consists of three parallel subsystems using XLS-R models with 300M, 1B, and 2B parameters as front-end feature extractors. Each subsystem employs learnable layer-wise feature fusion, followed by a Multi-kernel gated Convolution (MultiConv) module and Multi-Head Attention Pooling (MHAP) for utterance-level spoof detection. The output logits of the three independently trained subsystems are finally fused. The proposed system achieves an EER of 0.6575% on the evaluation set and ranks first in ArA-DF 2026 Track 2.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.190/
%P 1486-1490
Markdown (Informal)
[SparkShield at ArA-DF 2026: Robust Arabic Speech Deepfake Detection via Realistic Audio Augmentation and Multi-Scale XLS-R Score Fusion](https://aclanthology.org/2026.arabicnlp-sharedtasks.190/) (Fang et al., ArabicNLP 2026)
ACL