Attack-free WavLM detector ranks audio deepfakes but fails under shift
The best variant scores 8.45% EER on ASVspoof 2019 LA, then 22.12% EER on the 2021 DF shift.
Stories per day · 30 days
2 RSS
Relatedaudio-llm2ai-generated-video1anomaly-detection1artifact-detection1asvspoof1audio1generator-attribution1source-verification1verus-bench1verus-insight1wavlm1
10 stories, newest first · one card per story
Stories tagged #deepfake-detection
VeriSpoof audio LLM unifies deepfake detection and source verification
VeriSpoof achieves 2.14% EER for deepfake detection and generator verification across 14 test sets
VeriSpoof audio LLM unifies deepfake detection and source verification
VeriSpoof unifies five tasks with shared weights and releases open models achieving 2.14% EER on Speech-DF-Arena.
Verus-Insight targets explainable artifact detection in AI-generated video
The method splits detection into inspection planning, evidence verification, and aggregation, and is evaluated on a new human-annotated benchmark.
Google says 180 billion images and videos now carry SynthID watermarks as detector goes public
Google opened its SynthID Detector publicly and says over 180 billion images and videos carry its watermarks.
Modulate raises $25M for its voice models and analysis suite
Voice intelligence startup Modulate raised $25 million led by Future Ventures for transcription, intent analysis, and deepfake/scam detection across enterprise voice agents.
NVIDIA Brings Real-Time AI to Broadcast, Sports and Global Streaming at IBC
NVIDIA expanded its AI for Media suite at IBC 2026, adding NIM microservices for synthetic video detection, body pose, frame generation, upscaling and HDR.
4
What Makes Adversarial Examples Transfer Across Deepfake Detectors?
A controlled study of 60 deepfake detectors shows adversarial example transfer depends heavily on source-target compatibility, with source averaging understating vulnerability.
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection
UCF-Net fuses CLIP and DINO features with entropy-based uncertainty weighting to improve generalizable deepfake image detection across generators.
Adaptive Gated Deepfake Detection for Low-Resolution and Resource-Constrained Environments
AdaGate-DF routes deepfake detection by image quality through dual multi-exit gates, hitting 0.9370 AUC on Celeb-DF with low inference latency.