Reports

Forensic breakdowns

Step-by-step walkthroughs showing how ClipForensics analyzes videos — module by module, from raw data to verdict.

Face-swap deepfake breakdown

How ClipForensics detects a modern face-swap deepfake through multi-module analysis.

1

Metadata Analysis

File created with x264 encoder (not a camera). Creation timestamp recent. No GPS or camera model data.

Weak indicator — many legitimate videos are re-encoded with x264.

2

Compression History

Two encoding passes detected. First pass consistent with a screen recording tool. Second pass from social media re-encoding.

Moderate indicator — two passes suggest processing, but screen recording → upload is a common legitimate workflow.

3

Face Manipulation

Boundary artifacts detected at jawline in 73% of frames containing faces. Resolution mismatch between face region and background. Inconsistent noise patterns.

Strong indicator — these artifacts are characteristic of face-swap techniques.

4

Lip Sync

Phoneme-viseme misalignment exceeding baseline in 4 of 12 analyzed speech segments. Timing offsets of 80-120ms.

Moderate indicator — misalignment is present but could partially be explained by compression artifacts.

5

Temporal Consistency

Subtle flickering at face boundaries visible in optical flow analysis. Face region shows different temporal noise characteristics than background.

Strong supporting indicator — temporal inconsistency at face boundaries corroborates face manipulation finding.

6

Evidence Fusion

Face Manipulation (strong) + Lip Sync (moderate) + Temporal (strong support) = consensus across independent modules. No contradicting modules. Agreement bonus applied.

Verdict: High Manipulation Risk. Trust Score: 0.15. Confidence: High.

AI-generated video breakdown

How ClipForensics identifies a text-to-video generated clip.

1

Metadata Analysis

No camera metadata. Encoder identified as NVENC (GPU-based). No creation tool metadata.

Moderate indicator — absence of camera data is suspicious but not conclusive.

2

Spectral Analysis

Frequency domain shows characteristic patterns associated with diffusion-model upsampling. Periodic energy spikes at specific spatial frequencies.

Strong indicator — these spectral patterns are not produced by camera sensors or traditional editing.

3

Biological Motion

Human figure in video shows subtle gait anomalies. Eye blink rate (2.1/min) significantly below natural range (15-20/min). Hand movements show micro-jitter inconsistent with natural motor control.

Strong indicator — biological motion patterns differ significantly from natural human movement.

4

Optical Flow

Minor temporal morphing detected — objects gradually change shape over 10-15 frame windows. Background elements show subtle drift.

Moderate indicator — consistent with AI generation but could also indicate heavy post-processing.

5

Audio Synthesis

Speech shows spectral patterns consistent with neural TTS. Breathing absent between phrases. Environmental acoustics don't match visual environment.

Strong indicator — audio is synthetically generated.

6

Evidence Fusion

Spectral (strong) + Bio Motion (strong) + Audio Synthesis (strong) + Optical Flow (moderate) = broad consensus. Metadata supports. No contradictions.

Verdict: Likely AI-Generated. Trust Score: 0.11. Confidence: High.

See your own forensic breakdown

Upload a video for step-by-step analysis.