FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection

2026-09-16

AI Summary

针对音频反欺诈检测中适应性差的问题，提出FRAUDSkill框架，通过优化外部技能程序而不改变基础模型，实现高效且适应性强的解决方案。

Abstract

Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their deployment, however, requires predictions to follow a predefined label space and a structured decision protocol consisting of service-scenario identification, fraud detection, and conditional fraud-type classification. Existing fine-tuning and prompt-based approaches typically encode task knowledge, constraints, and decision rules into model parameters or manually maintained prompts, making them difficult to adapt as fraud patterns and labeling policies evolve. To this end, we propose FRAUDSkill, a structured frozen-weight adaptation framework that leaves the underlying audio-language model unchanged while optimizing an external layer of skill programs, route-specific policies, and decision rules. We further combine structured output control with validation-guided multi-path inference to ensure protocol-compliant predictions. On the TeleAntiFraud benchmark, FRAUDSkill achieves 73.50% Macro-F1, outperforming the shared frozen-model baseline by 31.96% while reducing invalid outputs to 1.94%. Extensive experiments demonstrate that external skill optimization provides an effective and adaptable solution for structured audio anti-fraud detection without modifying the underlying model. The source code is available at https://anonymous.4open.science/r/FRAUDSKILL-114514.

Problem

• audio anti-fraud detection
• structured decision protocol
• evolving fraud patterns
• labeling policies
• adaptability

Innovation

• Structured Frozen-Weight Adaptation
• External Skill Optimization
• Validation-Guided Multi-Path Inference
• Protocol-Compliant Predictions