Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection
cs.SD, cs.AI
Submitted: 2026-09-17
Updated: 2026-09-17
License: http://creativecommons.org/licenses/by/4.0/
The gist: The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security risks in practical applications.
Terminology
Abstract
The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security risks in practical applications. While existing detection methods achieve strong performance under controlled conditions, they often fail to generalize under real-world perturbations and corruptions. In this paper, we propose ROGUE, a framework that dynamically constructs robust detection workflows by orchestrating multiple detection tools. ROGUE formulates workflow generation as a sequential decision-making problem and introduces a dual-agent paradigm, where a perturbation agent generates audio perturbations and a policy agent learns to select and execute detection tools under perturbed conditions. Through adversarial learning, ROGUE enables perturbation-aware tool selection, adaptive execution strategies, and improved robustness to distribution shifts. Extensive experiments across multiple datasets and real-world corruptions demonstrate that ROGUE consistently outperforms strong baselines in both robustness and generalization. Our results highlight the effectiveness of adversarially optimized workflow generation for building reliable audio deepfake detection systems in real-world deployment settings.
Sources
- Audiobox: Unified Audio Generation with Natural Language Prompts
- FlashSpeech: Efficient Zero-Shot Speech Synthesis
- Investigating self-supervised front ends for speech spoofing countermeasures
- TextGrad: Automatic "Differentiation" via Text
- AutoFlow: Automated Workflow Generation for Large Language Model Agents
- ReAct: Synergizing Reasoning and Acting in Language Models
- Automated Design of Agentic Systems
- AFlow: Automating Agentic Workflow Generation
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- RobustFlow: Towards Robust Agentic Workflow Generation
- I Can Hear You: Selective Robust Training for Deepfake Audio Detection
- Explaining and Harnessing Adversarial Examples
- WaveFake: A Data Set to Facilitate Audio Deepfake Detection
- ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
- Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment