@inproceedings{lodagala-etal-2026-ara,
title = "{A}r{A}-{DF} 2026: Findings of the First Shared Task on {A}rabic Speech Deepfake Detection",
author = "Lodagala, Vasista Sai and
El Kheir, Yassine and
Althubaiti, Sara and
Mengibar, Pedro Jose Moreno and
Ali, Ahmed",
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.189/",
pages = "1473--1485",
ISBN = "979-8-89176-497-2",
abstract = "We present ArA-DF 2026, the first shared task for Arabic speech deepfake detection, held at ArabicNLP-2026. Unlike existing benchmarks that conflate all distribution shift into a single evaluation set, ArA-DF 2026 separates dialect generalization (Track 1: unseen Arabic dialects and speakers) from acoustic robustness (Track 2: codec compression, noise, reverberation, re-encoding). We release 43,500 labeled training utterances spanning MSA and regional dialects, plus blind evaluation sets of 144,210 (Track 1) and 127,746 (Track 2) utterances, ranking systems by EER. Fourteen teams competed on Track 1 and twelve on Track 2, with eight system description papers submitted. The best submissions cut EER from 14.54{\%} to 0.87{\%} (Track 1) and from 27.11{\%} to 0.66{\%} (Track 2). Across independent submissions, three findings recur: augmentation and data curation move performance far more than architecture; simpler pooling heads often outperform graph-attention back-ends once augmentation is applied; and external synthetic Arabic speech with mismatched generation artifacts hurts rather than helps. Residual errors concentrate on short utterances and on spoofed audio misclassified as bona fide."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lodagala-etal-2026-ara">
<titleInfo>
<title>ArA-DF 2026: Findings of the First Shared Task on Arabic Speech Deepfake Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vasista</namePart>
<namePart type="given">Sai</namePart>
<namePart type="family">Lodagala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yassine</namePart>
<namePart type="family">El Kheir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Althubaiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Jose</namePart>
<namePart type="given">Moreno</namePart>
<namePart type="family">Mengibar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</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>We present ArA-DF 2026, the first shared task for Arabic speech deepfake detection, held at ArabicNLP-2026. Unlike existing benchmarks that conflate all distribution shift into a single evaluation set, ArA-DF 2026 separates dialect generalization (Track 1: unseen Arabic dialects and speakers) from acoustic robustness (Track 2: codec compression, noise, reverberation, re-encoding). We release 43,500 labeled training utterances spanning MSA and regional dialects, plus blind evaluation sets of 144,210 (Track 1) and 127,746 (Track 2) utterances, ranking systems by EER. Fourteen teams competed on Track 1 and twelve on Track 2, with eight system description papers submitted. The best submissions cut EER from 14.54% to 0.87% (Track 1) and from 27.11% to 0.66% (Track 2). Across independent submissions, three findings recur: augmentation and data curation move performance far more than architecture; simpler pooling heads often outperform graph-attention back-ends once augmentation is applied; and external synthetic Arabic speech with mismatched generation artifacts hurts rather than helps. Residual errors concentrate on short utterances and on spoofed audio misclassified as bona fide.</abstract>
<identifier type="citekey">lodagala-etal-2026-ara</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.189/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1473</start>
<end>1485</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArA-DF 2026: Findings of the First Shared Task on Arabic Speech Deepfake Detection
%A Lodagala, Vasista Sai
%A El Kheir, Yassine
%A Althubaiti, Sara
%A Mengibar, Pedro Jose Moreno
%A Ali, Ahmed
%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 lodagala-etal-2026-ara
%X We present ArA-DF 2026, the first shared task for Arabic speech deepfake detection, held at ArabicNLP-2026. Unlike existing benchmarks that conflate all distribution shift into a single evaluation set, ArA-DF 2026 separates dialect generalization (Track 1: unseen Arabic dialects and speakers) from acoustic robustness (Track 2: codec compression, noise, reverberation, re-encoding). We release 43,500 labeled training utterances spanning MSA and regional dialects, plus blind evaluation sets of 144,210 (Track 1) and 127,746 (Track 2) utterances, ranking systems by EER. Fourteen teams competed on Track 1 and twelve on Track 2, with eight system description papers submitted. The best submissions cut EER from 14.54% to 0.87% (Track 1) and from 27.11% to 0.66% (Track 2). Across independent submissions, three findings recur: augmentation and data curation move performance far more than architecture; simpler pooling heads often outperform graph-attention back-ends once augmentation is applied; and external synthetic Arabic speech with mismatched generation artifacts hurts rather than helps. Residual errors concentrate on short utterances and on spoofed audio misclassified as bona fide.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.189/
%P 1473-1485
Markdown (Informal)
[ArA-DF 2026: Findings of the First Shared Task on Arabic Speech Deepfake Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.189/) (Lodagala et al., ArabicNLP 2026)
ACL