AI Paper Atlas

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

FUSE: Full‑spectrum Unlearnable Examples via Spectral Equalization

Jiale Cai, Gezheng Xu, Zhihao Li, Ruiyi Fang, Ruizhi Pu, Di Wu, Qicheng Lao, Charles Ling, Boyu Wang

ICML 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency

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 Random Spectral Masking (ablation)FUSE · CIFAR-10 low-pass 0.5, ResNet-18test accuracy: 57.35 -> 10.13Improved
add entropy regularizer (ablation)FUSE · CIFAR-10 low-pass 0.5, ResNet-18test accuracy: 15.13 -> 10.13Improved
add Cross-Band Guidance (ablation)FUSE · CIFAR-10 low-pass 0.5, ResNet-18test accuracy: 17.00 -> 10.13Improved
add Random Spectral Masking, unfiltered-like cutoff 1.0 (ablation)FUSE · CIFAR-10 cutoff 1.0, ResNet-18test accuracy: 11.13 -> 9.41Improved
set frequency split radius r_c to 0.5 instead of 0.2 (ablation)FUSE · CIFAR-10 low-pass 0.5test accuracy: 10.93 -> 10.13Improved
set frequency split radius r_c to 0.5 instead of 0.8 (ablation)FUSE · CIFAR-10 low-pass 0.5test accuracy: 14.70 -> 10.13Improved
use moderate lambda around 0.5 rather than very small or very large (ablation)FUSE · CIFAR-10, CIFAR-100, SVHNtest accuracyImproved
increase perturbation bound from 2/255 to 8/255 (ablation)FUSE · CIFAR-10 unfilteredtest accuracy: 11.00 -> 9.41Improved
increase perturbation bound from 2/255 to 8/255 under low-pass (ablation)FUSE · CIFAR-10 low-pass 0.5test accuracy: 15.53 -> 10.13Improved
apply low-pass filtering to protected dataLSP · CIFAR-10 ResNet-18test accuracy: 13.54 -> 54.16Hurt
apply low-pass filtering to protected dataFUSE · CIFAR-10 ResNet-18test accuracy: 9.41 -> 10.13No clear effect
apply Mixup augmentation defenseOPS · CIFAR-10 ResNet-18test accuracy: 15.56 -> 33.13Hurt

Later papers that compared with this method

1 later accepted paper reports Fuse as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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