AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection

Ido Nitzan Hidekel, Gal Lifshitz, Khen Cohen, Dan Raviv

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SRM high-pass noise branch and JS alignment loss to dual XLSR encoders (ablation)SONAR-Full · In-the-WildEER (%): 8.91 -> 6.00Improved
add JS alignment loss (ablation)SONAR-Full · ITWEER (%): 8.50 -> 6.00Improved
add JS alignment loss (ablation)SONAR-Full · ASVspoof 2021 LAEER (%): 2.90 -> 1.55Improved
use learnable SRM filters instead of fixed ones (ablation)SONAR-Full · In-the-WildEER (%): 8.20 -> 6.00Improved
add the SRM rich feature extractor (ablation)SONAR-Full · In-the-WildEER (%): 8.44 -> 6.00Improved
use separate (unshared) XLSR encoder weights for content and noise branches (ablation)SONAR-Full · In-the-WildEER (%): 8.40 -> 6.00Improved
increase number of SRM filters from 1 to 30 (ablation)SONAR-Full · In-the-WildEER (%): 8.00 (M=1) -> 7.40 (M=10) -> 6.00 (M=30)Improved
raise JS loss weight lambda from 0.5 to 1 (ablation)SONAR-Full · In-the-WildEER (%): 7.91 (0.5) -> 7.02 (0.8) -> 6.00 (1)Improved
add SONAR NFE and JS alignment to pre-trained XLSR-MambaXLSR-Mamba · In-the-WildEER (%): 6.71 -> 5.43Improved
add SONAR to XLSR-MambaXLSR-Mamba · ASVspoof 2021 LAEER (%): 0.93 -> 1.20Hurt
add SONAR alignment to baseline encodersXLSR-AASIST and XLSR-Mamba · In-the-Wild high-pass >4 kHz probeEER (%): 32.51 -> 26.57; 29.77 -> 26.08Improved
replace AASIST head with two-layer MLP (ablation)SONAR · In-the-WildEER (%): 6.00 -> 6.98Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy