AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks

Yixiao Xu, Binxing Fang, Rui Wang, Yinghai Zhou, Yuan Liu, Mohan Li, Zhihong Tian

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Neural network watermarking · 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
use composite trigger instead of white pixel block (ablation)Neural Honeytrace · CIFAR-10average watermark success rate: 37.86% -> 58.60%Improved
use composite trigger instead of semantic object (ablation)Neural Honeytrace · CIFAR-10average watermark success rate: 25.08% -> 58.60%Improved
attacker queries with in-distribution CIFAR-10 instead of TinyImageNet (ablation)Neural Honeytrace · CIFAR-10average watermark success rate: 58.60% -> 29.18%Hurt
attacker queries with CIFAR-100 instead of TinyImageNet (ablation)Neural Honeytrace · CIFAR-10average watermark success rate: 58.60% -> 48.78%Hurt
VGG-16 target with ResNet-18 surrogate (architecture mismatch) (ablation)Neural Honeytrace · CIFAR-100 teacher-student pairsminimum watermark success rate: 43.80%No clear effect
increase attacker query sample size from 5,000 to 50,000 (ablation)Neural Honeytrace · CIFAR-10watermark success rateNo clear effect
larger d and smaller alpha, beta (ablation)Neural Honeytrace · CIFAR-10watermark strength vs protected accuracyMixed
increase CLP pruning strength against watermark (ablation)Neural Honeytrace · CIFAR-10watermark success rateNo clear effect
replace MEA-Defender with Neural HoneytraceMEA-Defender · CIFAR-10minimum watermark success rate: 11.60% -> 36.60%Improved
replace MEA-Defender with Neural HoneytraceMEA-Defender · CUB-200average watermark success rate: 53.52% -> 44.12%Hurt
replace MEA-Defender with Neural HoneytraceMEA-Defender · CUB-200 ownership assertionqueries to assert ownership: 24{,}156 -> 590Improved
replace MEA-Defender with Neural HoneytraceMEA-Defender · CIFAR-100average watermark success rate: 19.80% -> 55.62%Improved

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