CloakLM: Obfuscating GPU Memory Layout to Mitigate Model Ex-filtration for Serving (opens in new tab)

Large foundation models deployed on third-party and shared accelerator infrastructure face a practical risk of model exfiltration that existing defenses do not fully address. In common serving deployments, model providers control the VM or bare-metal serving stack but not the surrounding hardware substrate. The host to GPU interconnect, accelerator fabric, and neighboring infrastructure components remain outside the tenant's trust boundary and h...