paper-with-me

Papers

Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors

2026-06-28 · Nicolas M. Müller, Aditya Tirumala Bukkapatnam, Zohaib Ahmed arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.29544

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Deepfake DetectionAdversarial Robustness

Similar Papers 제목 키워드 기반

Automating Exploratory Multiomics Research via Language Models

2025-06-09 · Shang Qu, Ning Ding, Linhai Xie, Yifei Li 외

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…

Navigate

Proteus: Preserving Model Confidentiality during Graph Optimizations

2024-04-18 · Yubo Gao, Maryam Haghifam, Christina Giannoula, Renbo Tu 외

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 Optimization

Constrained Adversarial Learning for Automated Software Testing: a literature review

2023-03-14 · João Vitorino, Tiago Dias, Tiago Fonseca, Eva Maia 외

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 testing

Automating Exploratory Proteomics Research via Language Models

2024-11-06 · Ning Ding, Shang Qu, Linhai Xie, Yifei Li 외

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 discovery

Proteus: A Self-Designing Range Filter

2022-06-30 · Eric R. Knorr, Baptiste Lemaire, Andrew Lim, Siqiang Luo 외

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…