Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection
It addresses the challenge of detecting latent defects in semiconductor manufacturing with extremely low failure rates and no labeled anomalies.
The paper introduces the first unsupervised anomaly detection framework using a Diffusion Transformer for IC latent defect screening, achieving state-of-the-art performance on industrial 16nm test data under extreme class imbalance.
Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the first unsupervised anomaly detection framework incorporating a Diffusion Transformer. Raw test measurements are first compressed by an autoencoder, then reshaped into a structured token sequence enriched with sinusoidal and per-device wafer-position embeddings. Anomaly scores are derived from the noise-prediction error over mid-range diffusion timesteps, enabling fast wafer-scale screening without any labeled defects or manual feature engineering. Our approach achieves state-of-the-art performance on industrial 16nm IC test data under extreme class imbalance, offering interpretable failure localization through latent-space reconstruction residuals.