← Back to all news
arXiv Machine Learning

Interpreting SSL Representations for Spoof Detection: a WavLM Study

The study investigates which layers of the self‑supervised speech model WavLM carry the most spoof‑relevant information for spoof detection. Using the ASVspoof 5 database, the authors perform per‑layer linear probing, canonical correlation analysis (CCA) with acoustic features, and a grid search over layer subsets, finding that five specific layers outperform pooling all thirteen. CCA shows mid‑layers align with most acoustic features, while voice‑quality metrics correlate more with later layers, and visualizations suggest deeper layers encode general synthesis artifacts rather than attack‑specific signatures.

Related stories

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
multimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 25

Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?

The paper investigates whether the Voxtral audio‑language model can detect speech spoofing. It shows that without task‑specific adaptation, the model’s language‑model layers prioritize semantic content, making spoof‑discriminative acoustic cues less separable. By applying lightweight weight‑decomposed low‑rank adaptation (DoRA), the authors create Spooftral, which achieves an equal error rate of 4.25% on the ASVspoof5 evaluation set.

By Avishai Weizman, Yehuda Ben-Shimol, Itshak Lapidot
llmsmultimodal
More like this →
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
ragsafety
More like this →
arXiv AI
Jun 10

Linguistically Augmented Audio Speech Data (LinguAS)

arXiv:2606. 10246v1 Announce Type: cross Abstract: Maliciously-created fake speech, including deepfaked and spoofed audio, is proliferating at an alarming rate, and detection models are racing to stay ahead of the curve.

By Ashley R. Keaton, Zahra Khanjani, Christine Mallinson, Vandana P. Janeja
More like this →