用XAI证据增强大模型，让语音伪造检测解释更可信
XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models
- 用XAI信号引导多模态大模型生成可解释的检测理由
- 在PartialSpoof数据集上提升内部准确率45%以上
- 无需训练，适合需要可信解释的AI安全场景
语音深度伪造检测（SDD）系统需提供可信解释以保障决策可靠性。现有解释方法分为两类：传统可解释人工智能（XAI）如基于梯度的归因，生成与模型决策紧密耦合的低级信号，人类难以理解；而基于大语言模型（LLM）的解释常因缺乏启发式证据和任务特定监督，产生泛化且无根据的描述，根源在于SDD领域缺乏高质量的可解释数据集。为此，我们提出一种无需训练的解释框架，将XAI证据与多模态大模型结合，生成有依据且具体的解释。基于PartialSpoof数据集构建了可解释数据集，实验表明引入XAI的方法使内部准确率提升超过45%，并通过人工评估与忠实性检查验证。
原文摘要 · Abstract (English)
Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45\%, verified through human evaluation and faithfulness checks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。