AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection

2026-08-24

AI Summary

本文提出AT-ADD基准测试，旨在解决全类型音频深度伪造检测问题，通过两大赛道评估模型在不同条件下的鲁棒性及泛化能力。

Abstract

Recent audio generation models can synthesize high-fidelity speech, environmental sound, singing voice, and music, creating new risks for multimedia trust. Existing audio deepfake detection (ADD) benchmarks remain predominantly speech-centric and often underrepresent realistic channel variation and diverse audio types. This paper presents AT-ADD, a large-scale benchmark and challenge designed to evaluate both robust speech deepfake detection and all-type audio deepfake detection. Track 1 evaluates binary speech detection under unseen generators, diverse recording conditions, signal perturbations, and replay effects. Track 2 evaluates type-agnostic real/fake detection over speech, sound, singing, and music when the audio type is unknown at test time. We detail the dataset construction, evaluation protocol, and reproducible baselines, and analyze the final systems submitted to the ACM Multimedia 2026 Grand Challenge. The strongest official baseline obtains 76.73% and 79.47% Macro-F1 on the Track 1 and Track 2 evaluation sets, respectively, whereas the winning challenge systems reach 90.71% and 96.10%. Beyond aggregate rankings, sample-level analysis of the top five submissions examines generator- and type-level difficulty, cross-system error complementarity, and ranking stability. The results show that large-scale self-supervised representations, condition-aware augmentation, multi-crop inference, and structured fusion or routing are central to generalization, while generator-specific robustness and consistent performance across diverse audio types remain unresolved.

Problem

• Audio Deepfake Detection
• Robust Speech
• Diverse Audio Types

Innovation

• audio deepfake detection
• all-type audio
• self-supervised representation
• condition-aware augmentation
• multi-crop inference