Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
On the Evidentiary Limits of Membership Inference for Copyright Auditing
Murat Bilgehan Ertan, Emirhan Böge, Min Chen +2
As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used duri…
cs.CR2026
Function Recovery Attacks in Gate-Hiding Garbled Circuits using SAT Solving
Chao Yin, Zunchen Huang, Chenglu Jin +2
Semi-Private Function Evaluation (SPFE) enables joint computation while protecting both input data and the function itself. A practical instantiation is gate-hiding garbled circuit…