AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach

Guang Yang, Ziye Geng, Yihang Chen, Changqing Luo

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Decision-boundary geometry of robustness · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
place fingerprints at a stretch factor chosen inside the theoretical admissible interval, rather than fixed bounds or margins (ablation)AnaFP · CIFAR-10 CNNAUCImproved
discard infeasible stretch factors (vs C-lower/C-upper fixed to bounds) (ablation)AnaFP · CIFAR-10 CNNAUCImproved
use high-confidence anchors (margin >= 5.0) instead of mid-confidence (ablation)AnaFP · CIFAR-10 CNNAUC: 0.791 -> 0.958Improved
use high-confidence anchors (margin >= 5.0) instead of mid-confidence (ablation)AnaFP · MNIST MLPAUC: 0.755 -> 0.961Improved
moderately relax quantile thresholds from 0.3/0.7 to 0.5/0.5 (ablation)AnaFP · CIFAR-10 CNNAUC: 0.848 -> 0.957Improved
excessively relax quantile thresholds to 0.9/0.1 (ablation)AnaFP · CIFAR-10 CNNAUC: 0.959 -> 0.896Hurt
increase surrogate pool diversity from low to medium/high (ablation)AnaFP · CIFAR-10 CNNAUCNo clear effect
increase surrogate pool size beyond 6 models (ablation)AnaFP · CIFAR-10 CNNAUCNo clear effect
use AnaFP instead of baselines under KD attackfingerprinting · CIFAR-100 CNN, KDAUC: 0.596 vs 0.598 (UAP)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy