一句话：提出面向音频内容审核软件的蜕变测试框架MTAM，用音频扰动生成可绕过检测的有害测试用例。
音频平台常被用于传播仇恨言论、欺骗广告和色情内容，审核工具成为关键防线；但攻击者可通过改变音高、插入噪声等细微扰动绕过检测，现有工具对此类对抗输入的效果缺乏系统研究。本文提出蜕变测试框架MTAM：基于先导研究定义14条蜕变关系，分为音频特征扰动和启发式扰动两类，对有害音频生成仍具危害但更易逃逸检测的测试用例。MTAM测试五款商业审核软件和一个学术模型，商业软件最高错误发现率为16.7%–51.1%，学术模型为45.7%。重训练后模型鲁棒性提升（错误发现率接近0%），且原准确率保持。
The rapid growth of audio-centric platforms and applications such as Whatsapp and Twitter has transformed the way people communicate and share audio content in modern society. However, these platforms are increasingly misused to disseminate harmful audio content, such as hate speech, deceptive advertisements, and explicit material, which can have significant negative consequences (e.g., detrimental effects on mental health). In response, researchers and practitioners have been actively developing and deploying audio content moderation tools to tackle this issue. Despite these efforts, malicious actors can bypass moderation systems by making subtle alterations to audio content, such as modifying pitch or inserting noise. Moreover, the effectiveness of modern audio moderation tools against such adversarial inputs remains insufficiently studied. To address these challenges, we propose MTAM, a Metamorphic Testing framework for Audio content Moderation software. Specifically, we conduct a pilot study on 2000 audio clips and define 14 metamorphic relations across two perturbation categories: Audio Features-Based and Heuristic perturbations. MTAM applies these metamorphic relations to toxic audio content to generate test cases that remain harmful while being more likely to evade detection. In our evaluation, we employ MTAM to test five commercial textual content moderation software and an academic model against three kinds of toxic content. The results show that MTAM achieves up to 38.6%, 18.3%, 35.1%, 16.7%, and 51.1% error finding rates (EFR) when testing commercial moderation software provided by Gladia, Assembly AI, Baidu, Nextdata, and Tencent respectively, and it obtains up to 45.7% EFR when testing the state-of-the-art algorithms from the academy. In addition, we leverage the test cases generated by MTAM to retrain the model we explored, which largely improves model robustness (nearly 0% EFR) while maintaining the accuracy on the original test set. We release the code and experiment data to facilitate future research1.
DOI 原文 ·
@inproceedings{paperbot9540,
title = {Metamorphic Testing for Audio Content Moderation Software},
author = {Wenxuan Wang and Yongjiang Wu and Junyuan Zhang and Shuqing Li and Yun Peng and Wenting Chen and Shuai Wang and Michael R. Lyu},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00239}
}