Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose \textbf{SAFE-QAQ}, an end-to-end comprehensive framework for audio-based slow-thinking fraud detection. First, the SAFE-QAQ framework eliminates the impact of transcription errors on detection performance. Secondly, we propose rule-based slow-thinking reward mechanisms that systematically guide the system to identify fraud-indicative patterns by accurately capturing fine-grained audio details, through hierarchical reasoning processes. Besides, our framework introduces a dynamic risk assessment framework during live calls, enabling early detection and prevention of fraud. Experiments on the TeleAntiFraud-Bench demonstrate that SAFE-QAQ achieves dramatic improvements over existing methods in multiple key dimensions, including accuracy, inference efficiency, and real-time processing capabilities. Currently deployed and analyzing over 70,000 calls daily, SAFE-QAQ effectively automates complex fraud detection, reducing human workload and financial losses. Code: https://anonymous.4open.science/r/SAFE-QAQ.

翻译：现有欺诈检测方法主要依赖转录文本，易受自动语音识别（ASR）错误影响，且缺失语调、环境背景等关键声学线索，限制了其对复杂欺骗策略的检测效能。为应对这些挑战，我们首次提出\textbf{SAFE-QAQ}——一个端到端的、基于音频的慢思考欺诈检测综合框架。首先，SAFE-QAQ框架消除了转录错误对检测性能的影响。其次，我们提出基于规则的慢思考奖励机制，通过分层推理过程精准捕捉细粒度音频细节，从而系统性地引导模型识别欺诈指示性模式。此外，本框架在实时通话中引入了动态风险评估机制，实现了欺诈的早期检测与预防。在TeleAntiFraud-Bench数据集上的实验表明，SAFE-QAQ在准确率、推理效率和实时处理能力等多个关键维度上均显著优于现有方法。目前该系统已部署上线，每日分析超70,000通电话，有效实现了复杂欺诈检测的自动化，降低了人工工作量与经济损失。代码地址：https://anonymous.4open.science/r/SAFE-QAQ。