aiqbench analysis
This paper introduces ROGUE, a framework that uses adversarial learning and dual-agent reinforcement learning to orchestrate robust workflows for detecting audio deepfakes under real-world perturbations. By dynamically selecting detection tools based on generated adversarial samples, the system significantly improves generalization beyond controlled evaluation environments. This approach directly addresses the critical need for reliable AI security mechanisms against evolving synthetic media threats.
Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection
arXiv:2609.20063v1 Announce Type: cross 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.
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.
Sound (cs.SD); Artificial Intelligence (cs.AI)
arXiv:2609.20063 [cs.SD]
(or arXiv:2609.20063v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2609.20063 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
A Multi-Domain Feature Fusion Framework for Generalizable Deepfake Detection Across Different Generators
arXiv · Jun 15, 2026
[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
Latent Space · Oct 14, 2026
Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning
arXiv · Oct 7, 2026
End-to-End Multimodal Data Augmentation and Adversarial Robustness Benchmark with AugLy for Images, Text, Audio, and PyTorch
MarkTechPost · Sep 26, 2026