Chaonan Chan is a senior staff engineer at Phison, specializing in system-on-chip design, verification and implementation. With deep expertise in SoC IP integration, timing and power analysis, and digital IC design, he collaborates across architecture, firmware, hardware and backend teams to deliver high-performance SSD and controller solutions.
As generative AI shifts toward hyper-personalization, the demand for "Personal AI Twins" has surged. However, current implementations face a critical trilemma: privacy concerns over raw data leaving the device, latency bottlenecks in software-based vector search on edge devices, and the lack of a secure model to own, govern, and benefit from personal data as an asset. Traditional storage architecture remains a passive repository, failing to meet the high-dimensional data processing needs of modern embeddings.
This presentation proposes a novel Hardware-Accelerated Personal AI Twin Storage Architecture. We redefine the SSD as an active "Sovereign Identity Vault" that integrates data acquisition, real-time embedding generation, and high-speed vector retrieval within a single encrypted hardware module. By shifting vector database operations (indexing and similarty search) directly onto the storage controller, we eliminate data movement overhead and ensure raw data remains physically isolated form the host OS and cloud.