AI Paper Atlas

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

Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

Lucas Görnhardt, Timo Bartels, Niklas Schwarz, Tim Fingscheidt

ECCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 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
replace one-hot output with Hadamard code and quantile detectorSegFormer MiT-B0 · Cityscapes val, all perturbationsGlobal AuROC: 72.1 -> 80.2Improved
replace one-hot output with Hadamard code and error detectorDeepLabv3+ · Cityscapes val, all perturbationsGlobal AuROC: 72.5 -> 80.4Improved
replace one-hot output with Hadamard code and error detectorSegFormer MiT-B0 · BDD100K val, all perturbationsGlobal AuROC: 62.0 -> 70.3Improved
replace one-hot output with Hadamard code and error detectorDeepLabv3+ · BDD100K val, all perturbationsGlobal AuROC: 59.2 -> 70.9Improved
replace one-hot output with Hadamard codeSegFormer MiT-B0 · Cityscapes val, cleanmIoU: 76.4 -> 76.5No clear effect
replace one-hot output with Hadamard codeDeepLabv3+ · Cityscapes val, cleanmIoU: 80.2 -> 80.1No clear effect
replace one-hot output with Hadamard codeSegFormer MiT-B0 · BDD100K val, cleanmIoU: 59.5 -> 57.6Hurt
replace one-hot output with Hadamard codeDeepLabv3+ · BDD100K val, cleanmIoU: 59.8 -> 57.2Hurt
use quantile anomaly score instead of regression score (ablation)HadamardNet SegFormer MiT-B0 · Cityscapes val, all perturbationsGlobal AuROC: 74.6 -> 80.2Improved
use quantile anomaly score instead of error score (ablation)HadamardNet SegFormer MiT-B0 · Cityscapes val, Metzen attackGlobal AuROC: 68.4 -> 75.9Improved
use Hadamard quantile detector instead of entropySegFormer MiT-B0 · Cityscapes val, Metzen attackGlobal AuROC: 45.0 -> 75.9Improved
use Hadamard quantile detector instead of FGSM-optimized detector of Maag et al.SegFormer MiT-B0 · Cityscapes val, FGSM attackGlobal AuROC: 98.2 -> 95.9Hurt

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