Signals 4 · free daily AI digest

End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery

Paper recorded by Signals 4 on 2026-09-18 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21

Category: cs.LG · 机器学习 · first seen 2026-09-21

Abstract

The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Recently, attacks that extract these parameters using only oracle queries to a DNN have been actively studied at IACR conferences. The hard-label setting is the most challenging setting for model extraction, where an adversary can observe only the final

Read on arXiv →

#16 most recent of 235 cs.LG papers we have recorded · ↑ newer: Guiding Agents of Quantum Games to Equilibrium using Matrix Exponentia · ↓ older: Joint Remaining Useful Life Prediction and Capacity Estimation of Lith
Cite this page: End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery: the #16 most recent of 235 cs.LG papers we have recorded (as of 2026-09-18). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/end-to-end-hard-label-cryptanalytic-model-extraction-using-efficient-sign-recove.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions