Skip to content
Sagan

Paper

CloakLM: Obfuscating GPU Memory Layout to Mitigate Model Ex-filtration for Serving

Unreadunread

AI summary

arXiv:2606. 18400v1 Announce Type: cross Abstract: 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.