AI Paper Atlas

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

CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration

Ting Qiao, Yiming Li, Jianbin Li, Y. Q. Wang, Leyi Qi, Junfeng Guo, Ruili Feng, Dacheng Tao

TPAMI 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 6 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
add conformal calibration (CertDW vs CertDW-V) (ablation)CertDW-V · GTSRB BadNets, sigma 2.5VSR: 52 -> 72Improved
add conformal calibration (CertDW vs CertDW-V) (ablation)CertDW-V · GTSRB Blended (patch), sigma 2.5VSR: 46 -> 78Improved
add conformal calibration (CertDW vs CertDW-V) (ablation)CertDW-V · GTSRB Blended (noise), sigma 2.5WCA: 54 -> 80Improved
add conformal calibration (CertDW vs CertDW-V) (ablation)CertDW-V · CIFAR-10 BadNets, sigma 1.2WCA: 24 -> 36Improved
add conformal calibration (CertDW vs CertDW-V) (ablation)CertDW-V · CIFAR-10 Blended (noise), sigma 1.2WCA: 78 -> 78No clear effect
use certified verification instead of vanilla verification (ablation)Vanilla · GTSRB BadNets, sigma 2.5WCA: 0 -> 48Improved
use certified verification instead of vanilla verification (ablation)Vanilla · GTSRB Blended (patch), sigma 1.5VSR: 80 -> 82No clear effect
use certified verification instead of vanilla verification (ablation)Vanilla · GTSRB Blended (noise), sigma 2.5VSR: 0 -> 96Improved
add Gaussian noise to verification samplesvanilla dataset watermark · CIFAR-10WSR: reduce WSR by 60%Hurt
add adversarial perturbation to verification samplesBlended watermark · verification sample spaceWSR: drop by over 80%Hurt
increase trigger size R from (0.3,0.8) to (0.8,1.3)CertDW · GTSRB, sigma 1.5certified region area: 0.193 -> 0.133Hurt
increase noise level sigma from 1.5 to 3.5CertDW · GTSRB, R in (0.8,1.3)certified region area: 0.133 -> 0.218Improved

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