← 研踪 PaperTrailarXiv:2606.18738 · v2
GRIDEX: Region-Grounded Forensic Explanations for Vocoder-Based Synthetic Speech
首次提交 2026-06-17 14:32
版本更新 2026-11-10 18:22
雷达观测 2026-11-11 13:08
摘要
The advancement of speech generation technologies has made artificial speech increasingly realistic. Although modern classifiers achieve high accuracy in deepfake detection, they do not indicate where spoof cues appear in the spectrogram and what they imply acoustically, limiting their usefulness in forensic settings. Manual analysis of full spectrograms is resource-intensive, so evidence should narrow attention to the most diagnostic regions. Moreover, existing explainability methods have limited capabilities in connecting contextual attributes to localized evidence, making explanations harder to verify. To overcome this limitation, we propose GRIDEX, a pipeline that, given a detector-flagged spectrogram, generates forensic explanations of its anomalies. The pipeline (i) selects top-$K$ anomalous regions in the spectrogram and (ii) produces an explanation for each anomaly. The explanations follow a schema of categorical acoustic fields, including temporal, spectral, and phonetic information, as well as interpretation text. To our knowledge, this is the first framework to generate structured forensic explanations using region-grounded evidence in a controlled vocoder-based setting. GRIDEX is trained with a staged learning recipe that combines supervised fine-tuning (SFT) with Group Relative Policy Optimization (GRPO). Experiments on our dataset show improved artifact localization and explanation grounding quality over strong vision-language model (VLM) baselines.
作者备注：Accepted at ACML 2026. 16 pages. Updated title and manuscript to the accepted version
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-10 18:22 · 最新观测版本
GRIDEX: Region-Grounded Forensic Explanations for Vocoder-Based Synthetic Speech
The advancement of speech generation technologies has made artificial speech increasingly realistic. Although modern classifiers achieve high accuracy in deepfake detection, they do not indicate where spoof cues appear in the spectrogram and what they imply acoustically, limiting their usefulness in forensic settings. Manual analysis of full spectrograms is resource-intensive, so evidence should narrow attention to the most diagnostic regions. Moreover, existing explainability methods have limited capabilities in connecting contextual attributes to localized evidence, making explanations harder to verify. To overcome this limitation, we propose GRIDEX, a pipeline that, given a detector-flagged spectrogram, generates forensic explanations of its anomalies. The pipeline (i) selects top-$K$ anomalous regions in the spectrogram and (ii) produces an explanation for each anomaly. The explanations follow a schema of categorical acoustic fields, including temporal, spectral, and phonetic information, as well as interpretation text. To our knowledge, this is the first framework to generate structured forensic explanations using region-grounded evidence in a controlled vocoder-based setting. GRIDEX is trained with a staged learning recipe that combines supervised fine-tuning (SFT) with Group Relative Policy Optimization (GRPO). Experiments on our dataset show improved artifact localization and explanation grounding quality over strong vision-language model (VLM) baselines.
查看此版本解读 →查看此版本原文 ↗