LLMMedium
OpenAI's 4o Model Allegedly Used to Generate Fake Receipts and Prescriptions
- Occurred
- Mar 31, 2025
- Published
- Apr 7, 2025
- Source
- AI Incident Database
Summary
OpenAI's new image generator, 4o, was reportedly used to produce realistic fraudulent documents, including fake restaurant receipts, prescriptions for controlled substances, and potentially other identity or financial documents. Users demonstrated how the model could be prompted to bypass safety restrictions to be misused for expense fraud, medical forgery, and other various forms of document falsification.
Developers
- OpenAI
Deployers
- Scammers
Harmed parties
- Regulatory agencies
- Pharmacists
- Law enforcement
- healthcare providers
- General public
- Expense management platforms
- Employers
Tags
- AI image generation
- Document fraud
- Prescription forgery
- Expense fraud
- Model misuse
- OpenAI
- AI guardrails
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: LLM model misused for generating fraudulent documents, representing a notable failure with potential for harm but no confirmed mass casualties or legal action.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8