arXiv AI

Audio Physical Dynamics Inspired Deepfake Detection for Voice Authentication Systems

The paper proposes a framework for detecting deepfake audio in voice authentication systems at the network edge. It combines interpretable physics-based features that model vocal tract dynamics with representations from a self‑supervised learning module, processed through a streamlined MLP and a Bayesian ensemble to provide uncertainty estimates. The approach also includes a trust‑based aggregation protocol to protect the control plane from poisoning attacks in federated learning environments.

arXiv AI

Sep 12

A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems

The paper reviews how voice authentication has evolved from handcrafted acoustic features to deep learning speaker embeddings, expanding its use in finance, smart devices, and law enforcement. It surveys modern threats—including data poisoning, adversarial, deepfake, and adversarial spoofing attacks—tracing their development alongside technological advances. For each attack type, the authors summarize methods, datasets, performance, and limitations, and organize the literature using accepted taxonomies to highlight emerging risks and open challenges.

By Kamel Kamel, Keshav Sood, Hridoy Sankar Dutta, Sunil Aryal

rag safety

arXiv AI

Sep 12

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

The paper introduces the Spectral Masking and Interpolation Attack (SMIA), a black‑box adversarial technique that subtly alters inaudible frequency regions of AI‑generated audio to fool voice authentication systems and their countermeasures. Experiments show SMIA achieves at least 82% success against combined verification and countermeasure systems, 97.5% against standalone speaker verification, and 100% against countermeasures, revealing a critical security gap. The authors argue that current static defenses are inadequate and call for dynamic, context‑aware defenses that can adapt to evolving threats.

By Kamel Kamel, Hridoy Sankar Dutta, Keshav Sood, Sunil Aryal

multimodal benchmarks safety

arXiv AI

Jun 30

Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors

arXiv:2606. 29544v1 Announce Type: cross Abstract: We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system.

By Nicolas M. M\"uller, Aditya Tirumala Bukkapatnam, Zohaib Ahmed

agents reinforcement-learning safety

arXiv AI

5d ago

Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection

arXiv:2610.16049v1 Announce Type: cross Abstract: Existing audio deepfake detection (ADD) methods frequently exhibit limited generalization, as fixed bottleneck architectures fail to adapt to the het...

By Jianqiao Cui, Haoxian Zhu, Hanbiao Meng, Yanghao Zhang

multimodal benchmarks safety

arXiv AI

Sep 18

Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection

The paper introduces ROGUE, a framework that builds robust audio deepfake detection workflows by combining multiple detection tools. ROGUE treats workflow creation as a sequential decision problem and uses a dual-agent system: a perturbation agent generates audio distortions while a policy agent selects and executes detection tools that are resilient to those perturbations. Experiments on several datasets and real-world corruptions show that ROGUE consistently outperforms strong baselines in robustness and generalization, demonstrating the value of adversarially optimized workflow generation for reliable deployment.

By Xiang Li, Pin-Yu Chen, Wenqi Wei

agents safety

arXiv AI

Jul 1

Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin

arXiv:2606. 30780v1 Announce Type: cross Abstract: Audio deepfakes are a growing challenge for the general public, as well as for journalists and fact-checkers.

By Octavian Pascu, Dan Oneata, Horia Cucu, Nicolas M. Muller

efficiency safety

arXiv AI

Aug 11

MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection

arXiv:2608. 09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video.

By Yanqiu Li, Yang Xiao, Jisheng Bai, Bin Chen, Hong Jia, Ting Dang

llms robotics multimodal benchmarks

arXiv Machine Learning

Oct 8

Backdooring Acoustic Foundation Models for Physically Realizable Triggers

arXiv:2610.09819v1 Announce Type: cross Abstract: Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to spea...

By Zebin Yun, Eyal Ronen, Mahmood Sharif

fine-tuning multimodal benchmarks

arXiv AI

Jul 17

Large Audio Language Models for Spoofing-Aware Speaker Verification

arXiv:2607. 14753v1 Announce Type: cross Abstract: Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV).

By Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir, Artem Dvirniak, Dmitrii Korzh, Oleg Y. Rogov

llms multimodal

arXiv AI

Aug 12

From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

arXiv:2605. 27944v2 Announce Type: replace Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical.

By Ke Liu, Jiwei Wei, Wenyu Zhang, Shuchang Zhou, Ruikun Chai, Yutao Dai, Chaoning Zhang, Yang Yang

multimodal benchmarks

arXiv AI

Jul 21

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

arXiv:2607. 17761v1 Announce Type: cross Abstract: Recently, speech deepfake detection (SDD) has achieved significant progress.

By Jun Xue, Zhuolin Yi, Yanzhen Ren, Yihuan Huang, Jiayu Xiong, Yi Chai, Guanxiang Feng, Jiajun Liu, Tong Zhang

benchmarks safety

arXiv Machine Learning

Jul 20

Natural Backdoor Attacks on Speech Recognition Models

arXiv:2607. 15724v1 Announce Type: cross Abstract: With the rapid development of deep learning, its vulnerability has gradually emerged in recent years.

By Jinwen Xin, Xixiang Lyu, Jing Ma

multimodal

Related stories