Project AURIONAI Use-Cases Research & Innovation
Public Sector

Customs Risk Management and Trade Fraud Detection

Scores import and export declarations and cargo X-ray images for risk, checks customs value and classification, and flags under-invoicing, over-invoicing and other trade fraud.

Named Models

The research names no model for this use case.

Where this comes from
Models the research names for this use case. Research, with sources on each model record.

Who Runs It

production, 2pilot, 1
Direktorat Jenderal Bea dan Cukai (DJBC)Directorate General of Customs and Excise (DJBC), KPU Bea Cukai Soekarno-HattaCountry: IndonesiaAir cargo X-ray images integrated into CEISA 4.0 with AI-based lane assignment and a central X-ray image repository (model and vendor not named)Vendor: not statedproductionDate8 Oct 2026Mandatory stage 1 from 8 October 2026 (FedEx, RPX); all temporary storage sites from January 2027. FedEx trial from June 2026: clearance release up nearly 20 percent, X-ray handling time down about 30 percent (company claim)Evidence: government statementConfidence: mediumSource: fortuneidn.com, en.wikipedia.org
Direktorat Jenderal Bea dan Cukai (DJBC)Directorate General of Customs and Excise (DJBC), Ministry of FinanceCountry: IndonesiaSSR-Mobile (Self Service Report Mobile) in CEISA 4.0 with AI automated risk analysis (model not stated)Vendor: not statedproductionDate12 Dec 2025Finance Minister claims less bureaucracy, higher compliance and fewer gaps for fraudEvidence: government statementConfidence: mediumSource: ortax.org
Direktorat Jenderal Bea dan Cukai (DJBC)Directorate General of Customs and Excise (DJBC), Ministry of FinanceCountry: IndonesiaTradeAI: customs value, classification and document checks integrated with CEISA 4.0 (model not stated)Vendor: not statedpilotDate25 Mar 2026Early trial on nearly 150 import declarations found abnormal values worth an estimated Rp1.2 billion in extra revenue; document review time fell from 120 minutes to 50 to 60 minutes (DJBC 2025 performance report via DDTC)Evidence: government statementConfidence: mediumSource: news.ddtc.co.id, ortax.org
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

UltralyticsYOLO26lUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26mUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26nUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsUltralyticsYOLO26sUltralytics, visionReleasedJan 2026open weightsruns on edgehas scoreslast 18 monthsDMLC communityXGBoostDMLC community, tabularReleasedAug 2026open weightshas scoreslast 18 monthsMicrosoft AILightGBMMicrosoft AI, tabularReleasedJul 2026open weightshas scoreslast 18 monthsBaiduPaddleOCR-VL-1.6Baidu, OCR and documentReleasedJun 2026runs on edgehas scoreslast 18 monthsPrior LabsTabPFN-2.6Prior Labs, tabularReleasedMar 2026open weightshas scoreslast 18 monthsYandexCatBoostYandex, tabularReleasedFeb 2026open weightshas scoreslast 18 monthsZ.ai (Zhipu)GLM-OCRZ.ai (Zhipu), OCR and documentReleasedJan 2026open weightshas scoreslast 18 months

Showing 10 of 767. All models of this class

Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Sources

  1. news.ddtc.co.id/berita/nasional/1818199/djbc-kembangkan-ai-un... https://news.ddtc.co.id/berita/nasional/1818199/djbc-kembangkan-ai-untuk-awasi-impor-begini-progresnya
  2. ortax.org/bea-cukai-resmikan-pemindai-peti-kemas-dan-ke... https://ortax.org/bea-cukai-resmikan-pemindai-peti-kemas-dan-kenalkan-aplikasi-kepabeanan-berbasis-ai
  3. fortuneidn.com/news/bea-cukai-perketat-barang-impor-x-ray-ai... https://www.fortuneidn.com/news/bea-cukai-perketat-barang-impor-x-ray-ai-wajib-mulai-januari-2027-00-my5jv-rpy2d2

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Customs Risk Management and Trade Fraud Detection", https://aurion.semai.id/usecases/pub-customs-risk-management/, records of October 2026.