SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment
SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment explores A self-supervised framework for detecting audio-visual deepfakes by learning solely on authentic videos, overcoming dataset bias and improving generalization.. Commercial viability score: 7/10 in Deepfake Detection.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisAudio Deepfake Detection in the Age of Advanced Text-to-Speech modelsViability: 5.0
- Builds On ThisTowards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake DetectionViability: 3.0
- Prior WorkTRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation ModelsViability: 7.0
- Prior WorkUnleashing Vision-Language Semantics for Deepfake Video DetectionViability: 7.0
- Prior WorkmAVE: A Watermark for Joint Audio-Visual Generation Models