VeriSpoof: one audio LLM unifies deepfake detection, attribution and source verification
unimelb-hf · hf · 2026-11-05
The University of Melbourne released the VeriSpoof technical report (Nov 2026): an open audio language model that unifies speech forensics beyond a simple real-or-fake verdict.
- Unifies five tasks: deepfake detection, generator attribution (generator, acoustic model, vocoder), recording-condition analysis, synthesized-span localisation, and source verification
- Key design: every answer is a sentence whose likelihood can be independently verified, with grounded rationales where each statement is checkable
- Requires only minimal parameter updates across tasks
- Models, benchmark, code and a demo are open-sourced
More from Safety
- Template-based multilingual safety pipeline shows English-only evals misjudge alignment — swiss-ai · 2026-11-05
- User accidentally prompt-injects X's translation feature into serving a fried rice recipe — kingslyj · 2026-11-05
- Internal safeguards won't stop hostile AI, researcher argues for external defenses — IgorGabrielan · 2026-11-05
- Lightcone Commons opens applications with Jaan Tallinn and Moskovitz as funders — NathanpmYoung · 2026-11-05
- Debate: did a $4B California ballot push for a single AI lab mislead the public? — NathanpmYoung · 2026-11-05
- Orinyx: an open-source MCP for independently verifying AI agent outputs against evidence — Practical_Green5775 · 2026-11-05