2 papers
cs.CR2026
ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read Factor
Dominik Dahlem, Rui Vieira
Third-party adapters for open-weight language models ship as opaque weight matrices; a recipient cannot check whether an adapter hides a backdoor without trusting the publisher or…
cs.LG2026
Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics
Dominik Dahlem, Diego Maniloff, Mac Misiura
Every attention head defines a degree-normalized transport operator, and a growing family of diagnostics reads model behavior (hallucination among them) from its spectrum. We ask w…