Researchers at Hanyang University developed a light-driven true random number generator for embedding secure signatures into images and detecting tampering.
Key Details
- 1Hanyang University created a photospike-based true random number generator (PS-TRNG) using CuV2O6/SnO2 quantum-dot heterostructures.
- 2The device generates ternary random numbers in real time by exploiting stochastic charge trapping and de-trapping under pulsed light.
- 3Generated random numbers showed stability over 2 million cycles and 460 days, and passed all 15 NIST randomness tests.
- 4Random numbers can be embedded into images as security signatures, allowing detection of image modifications or AI-generated forgeries.
- 5Potential applications include secure medical image authentication and deepfake detection in sensitive domains.
Why It Matters
Embedding hardware-based entropy into image sensors enables pixel-level detection of image tampering and deepfakes at the point of acquisition, enhancing trust, security, and forensic capabilities in radiology and other fields.
Source
EurekAlert
Related News
•EurekAlert
AI Accelerates Radiopharmaceuticals, Boosts Personalized Dosimetry in Cancer
Machine learning is driving advancements in radiopharmaceutical drug discovery and optimizing patient-specific dosimetry for precision cancer therapy.
•EurekAlert
Physicians Overly Trust Erroneous AI, Ignore Contradictory Evidence
Physicians tend to trust incorrect AI advice, even when evidence contradicts it, suggesting risks in clinical decision-making with AI tools.
•EurekAlert
Concerns Raised Over Unverified Datasets in AI Health Prediction Models
A new study finds widely used AI health prediction models are built on datasets with unverifiable origins, raising safety and validity concerns.