AudioSeal generators fine-tuned against diffusion watermark-removal attacks (SGMSE, AudioLDM). Built at PSIML 11 in Serbia.
🤝 Open to Collab
Marat Saidov
msaidov
AI & ML interests
Applied Sciences and Windows AI at Microsoft. On-device language models. Speech and audio technologies. Efficient DL systems.
Recent Activity
liked a model 3 days ago
tencent/Hy-MT2-30B-A3B updated a collection 6 days ago
AudioSeal Robustness to Diffusion Attacks updated a collection 6 days ago
AudioSeal Robustness to Diffusion AttacksOrganizations
