Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors
We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system. Given a detector, Proteus systematically searches over sequences of everyday audio transformations (codec transcoding, additive noise, reverberation, dynamic-range compression, and VoIP simulation) to find combinations that fool the detector while preserving speech quality. We propose two complementary search strategies: (1) a breadth-first search that exhaustively maps augmentation effectiveness across the parameter space, and (2) a Q-learning agent designed to efficiently discover deeper attack chains by exploiting structural patterns in the BFS data. We report findings from continuous deployment of Proteus against our production detector, showing that specific augmentation chains can reliably flip detection verdicts while preserving speech intelligibility and speaker identity. We discuss how these findings are used to harden the detector through targeted retraining.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio Deepfake DetectionAdversarial RobustnessSimilar Papers 제목 키워드 기반
Automating Exploratory Multiomics Research via Language Models
This paper introduces PROTEUS, a fully automated system that produces data-driven hypotheses from raw data files. We apply PROTEUS to clinical proteogenomics, a field where effective downstream data analysis and hypothes…
NavigateProteus: Preserving Model Confidentiality during Graph Optimizations
Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typically involves two parties: the model deve…
Computational EfficiencymodelModel OptimizationConstrained Adversarial Learning for Automated Software Testing: a literature review
It is imperative to safeguard computer applications and information systems against the growing number of cyber-attacks. Automated software testing tools can be developed to quickly analyze many lines of code and detect …
Adversarial Attacksoftware testingAutomating Exploratory Proteomics Research via Language Models
With the development of artificial intelligence, its contribution to science is evolving from simulating a complex problem to automating entire research processes and producing novel discoveries. Achieving this advanceme…
scientific discoveryProteus: A Self-Designing Range Filter
We introduce Proteus, a novel self-designing approximate range filter, which configures itself based on sampled data in order to optimize its false positive rate (FPR) for a given space requirement. Proteus unifies the p…