🔐 Cryptographic Tamper Evidence

Video Fraud Evidence
You Can Prove in Court

FraudLens turns surveillance footage into tamper-evident, cryptographically sealed forensic records. Every annotation is chained to the original video — any edit breaks the chain.

See how it works
H₀ = sha256(raw_video_bytes)  ← genesis
H_f = sha256(frame_jpeg)       ← per frame
H_a = sha256(bbox+label+H₀)   ← per annotation
H_m = sha256(H₀+ΣH_a+sig)   ← seal — immutable

Five stages. One unbreakable chain.

From raw video drop to court-ready YOLO training record — every step is cryptographically linked.

01

Video Intake — Genesis Hash H₀

Drop your surveillance video. FraudLens extracts resolution, fps, codec, and duration via ffprobe, then streams the raw bytes through SHA-256 to produce H₀ — the root of the entire cryptographic chain.

ffprobe · sha256 · genesis block
02

Frame Sampling — AI Scene Read

ffmpeg samples 8–12 best-lit keyframes. Claude reads each frame and returns a suggestion list — desk, chair, cash, counter — so operators start annotating instantly, not from scratch.

ffmpeg · claude-3-5-sonnet · keyframes
03

Annotation — H_a per Bounding Box

Operators draw bounding boxes on frames, selecting tier (object / surface / area) and label. Each annotation is hashed: H_a = sha256(bbox + label + frame_id + H₀), linking it permanently to the genesis.

canvas · bbox · sha256 chain
04

Seal Manifest — H_m

The operator reviews and signs the manifest. FraudLens computes H_m = sha256(H₀ + all H_a + signature). The manifest is written to disk — immutable. Any subsequent edit breaks the chain.

sha256 · operator sig · immutable
05

Emit Training Data — YOLO Records

Faces are blurred, PII masked. YOLO-format label files are written with normalised bounding boxes, each traceable to H_m. Your AI model trains on forensically clean, court-admissible data.

anonymise · yolo · training store

Built for legal admissibility.

🔐

Unbreakable Hash Chain

SHA-256 links every annotation back to the raw video bytes. Any post-seal edit is immediately detectable — no exception.

🤖

AI-Assisted Annotation

Claude reads each sampled frame and suggests object labels, cutting annotation time by 60%. Custom labels are auto-enriched with explanatory notes.

🏛️

Court-Ready Export

Every manifest exports as a sealed JSON with full audit trail. H_m verification can be run by any third party — no proprietary tools required.

🎯

3-Tier Annotation Vocabulary

Objects (hand, cash, card), Surfaces (counter_top, drawer), Areas (customer_zone, POS_area) — plus unlimited custom labels with AI enrichment.

🛡️

PII Anonymisation

Faces are Gaussian-blurred and personal identifiers masked before any training data is emitted. GDPR and KVKK compliant by design.

📦

YOLO Training Output

Annotated frames export directly as YOLO-format label files — ready to feed YOLOv8, YOLOv11, or any compatible detector without conversion.


Simple, transparent pricing.

Pay in Turkish Lira via iyzico, or in crypto via NowPayments.

Starter
₺990/mo
For individual investigators
  • 5 engagements / month
  • Up to 2 hour video
  • AI label suggestions
  • YOLO export
  • Sealed manifest PDF
Enterprise
Custom
For banks, retailers, insurers
  • On-premise deployment
  • Custom annotation vocabulary
  • SLA + dedicated support
  • White-label option
  • Legal expert partnership

Payment methods:

💳 iyzico (TRY)
₿ Bitcoin
Ξ Ethereum
◎ USDT
+ 50 crypto via NowPayments

FraudLens Annotation Workspace

01 Intake
02 Frames
03 Annotate
04 Seal
05 Emit