AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Evading Data Provenance in Deep Neural Networks

Hongyu Zhu, Sichu Liang, Wenwen Wang, Zhuomeng Zhang, Fangqi Li, Shi-Lin Wang

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 0 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 transfer set curation (vs random LSVRC samples) (ablation)Escaping DOV · CIFAR-10 / NarcissusACC: 91.63 ± 0.49 -> 94.37 ± 0.18Improved
add transfer set curation (vs random LSVRC samples) (ablation)Escaping DOV · CIFAR-10 / NarcissusVSR: 7.87 ± 0.52 -> 4.59 ± 0.64Improved
use in-domain-like LSVRC curated set instead of GTSRB as transfer set (ablation)Escaping DOV · CIFAR-10 / NarcissusACC: 66.80 ± 0.41 -> 94.37 ± 0.18Improved
add transfer set curation (vs GTSRB) (ablation)Escaping DOV · CIFAR-10 / NarcissusVSR: 8.96 ± 1.63 -> 4.59 ± 0.64Improved
add selective knowledge transfer (SKT) (ablation)Escaping DOV · CIFAR-10 / Narcissus, varying temperatureVSR: VSR rises sharply without SKT at higher temperaturesImproved
raise distillation temperature (ablation)Escaping DOV · CIFAR-10 / NarcissusACC: test accuracy remains nearly unchangedNo clear effect
replace SKT offline perturbation pool with direct UAT on student (ablation)Escaping DOV · CIFAR-10 / NarcissusVSR / ACC: VSR 2.07%, accuracy reduction 3.54%Mixed
use curated transfer set instead of entropy-based DFND selectionEscaping DOV · CIFAR-10 / semantic backdoorVSR: 70.2% -> 17.4%Improved
add mixup in teacher trainingEscaping DOV · CIFAR-10 / NarcissusVSR: 4.59 -> 3.66Improved
add mixup in teacher trainingEscaping DOV · CIFAR-10 / Isotopep-value: 0.2845 -> 0.7013Improved
add mixup in teacher trainingEscaping DOV · CIFAR-10 / Dataset Inferencep-value: 0.4759 -> 0.5196Improved
increase ADB hyperparameter mu from 0.1 to 10Escaping DOV · CIFAR-10 / ADB watermarkVSR: 94.42% -> 14.21%Hurt

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