AI RESEARCH
Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators
arXiv CS.LG
•
ArXi:2604.23205v1 Announce Type: cross Deploying We present Tessera, a reference architecture for inline, cache-line granularity weight decryption on UMA edge accelerators. The design intercepts 64-byte AXI bursts, computing AES-256-CTR keystreams in parallel with DRAM fetches. This streams plaintext directly into isolated NPU SRAM, creating a transient memory footprint confined to the active tile and eliminating the need for permanent memory carve-outs.