works on
API security 1distillation attacks 1large language models 1output perturbation defenses 1threat modeling 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2026

What Does It Mean to Break a Distillation Defense?

Lena Libon, Pura Peetathawatchai, Michael Aerni +2

The paper examines how to evaluate defenses that add noise to large language model outputs to thwart distillation attacks, proposing a three‑dimensional threat model (query budget,…