Forensic Model Forensics

AI Model Artifacts & Deepfake Detector Directory

Technical breakdowns of the newest generative face-swapping, voice-cloning, and video-diffusion engines, with frame-by-frame artifact recognition.

Real-Time Face Swap ThreatCritical

Deep Live Cam Detector: Spotting Real-Time Webcam Face Swaps

Deep Live Cam went viral in 2024–2025 as an open-source tool enabling anyone to swap their face in real-time onto a live webcam stream using a single reference photo. It is heavily utilized by romance scammers, catfishes, and remote interview impostors on Zoom, Teams, and Omegle. Sealed Rose detects the distinct temporal jitter, edge blending blur, and lighting inconsistencies generated by Deep Live Cam’s ONNX model pipeline.

View Forensic Signatures
Neural Portrait AnimationHigh

LivePortrait AI Detector: Spotting Video & Audio Driven Face Animation

LivePortrait (developed by Kuaishou) generates lifelike animated talking videos from a single still portrait by transferring head movements, blinks, and emotional expressions from a driver video. It is widely used by catfish syndicates to turn stolen photos into "video proof" of their identity.

View Forensic Signatures
Offline Desktop Face SwapHigh

Roop Unleashed Deepfake Detector: Offline Video Face Swap Analysis

Roop Unleashed is a widely used desktop software application that automates face-swapping across full video clips without requiring dataset training. Attackers use it to generate non-consensual deepfakes and fabricate fake celebrity adult content.

View Forensic Signatures
Flow-Matching Voice SynthesisCritical

F5-TTS Voice Clone Detector: Zero-Shot Audio Deepfake Analysis

F5-TTS is a state-of-the-art open-source text-to-speech model based on flow matching. With just 3 to 5 seconds of audio from a podcast, voicemail, or Instagram story, F5-TTS clones an individual’s voice with unprecedented fidelity, fueling grandparents-in-jail phone scams and CEO fraud.

View Forensic Signatures
Commercial Chatter AIHigh

Chatterbox AI & Agency Chat Bot Detector: Spotting OnlyFans Chatters

OnlyFans agencies hire hundreds of remote chatters in the Philippines, Colombia, and Eastern Europe who use automated CRM tools and LLMs (Chatterbox AI, Infloww) to impersonate top models. They follow strict sales scripts designed to milk tips and PPV purchases from unsuspecting fans.

View Forensic Signatures
Open-Weights Video ModelModerate

Mochi 1 Video AI Detector: Genmo Open Video Model Forensics

Mochi 1 is an open-source video generation model from Genmo with 10 billion parameters. It produces high-motion video from text prompts, but exhibits distinctive fluid dynamics inconsistencies and unnatural physical inertia.

View Forensic Signatures
3D VAE Diffusion ModelModerate

CogVideoX-5B Video Detector: Zhipu AI Generation Forensics

CogVideoX-5B (developed by Zhipu AI) uses an expert 3D VAE to compress spatial and temporal dimensions. Sealed Rose inspects 3D VAE reconstruction bounds to identify synthetic video generated by this architecture.

View Forensic Signatures
Next-Gen Face SwapperCritical

FaceFusion Deepfake Detector: Next-Gen Video Face Swapping Forensics

FaceFusion is the premier open-source face-swapping and face-enhancement framework. It combines high-resolution face swapping (Ghost, Inswapper) with neural restoration (CodeFormer, GFPGAN) and frame color matching. Despite its photorealism, Sealed Rose detects the boundary masks and restoration artifacts left by FaceFusion.

View Forensic Signatures