RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations

TL;DR

The RADAR Challenge 2026 aims to advance robust audio deepfake detection across multiple languages and media transformations, providing a large dataset and evaluation framework to benchmark current systems.

Contribution

This paper introduces a comprehensive challenge with a new multilingual dataset and evaluation protocol to improve audio deepfake recognition under realistic media conditions.

Findings

33 teams participated in development phase

22 teams participated in evaluation phase

Results highlight ongoing challenges in multilingual and media-transformed deepfake detection

Abstract

RADAR Challenge 2026 is an APSIPA Grand Challenge on Robust Audio Deepfake Recognition under Media Transformations, designed to simulate realistic media conditions in real-world audio distribution pipelines, including compression, resampling, noise, and reverberation. It consists of two phases: an English development phase with labeled data for analysis and paper writing, and a multilingual evaluation phase containing more than 100,000 utterances in English, Singapore English, Mandarin Chinese, Taiwanese Mandarin, Japanese, and Vietnamese. Systems are evaluated using equal error rate (EER) for binary real/fake classification. This paper describes the challenge task, the construction of the data set, the evaluation protocol, and the overall results. During the challenge, 33 teams submitted to the development phase and 22 teams submitted to the final evaluation phase. The reported results highlight the remaining challenges of robust audio deepfake detection under multilingual and media-transformed conditions.