AI Paper Atlas

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

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

Jongheon Jeong, Sihyun Yu, Hankook Lee, Jinwoo Shin

CVPR 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 0 citations (OpenAlex)

This paper tried a common change: Add a reconstruction / auxiliary loss

Add the reconstruction loss · CIFAR-10 · accuracy Improved

What 987 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Train with AENIB rather than cross-entropyResNet-18 · CIFAR-10-Caverage corruption error rate: 16.0 -> 12.3Improved
Train with AENIB rather than PixMixResNet-18 · CIFAR-10.1test error rate: 13.1 -> 11.6Improved
Train with AENIB rather than the cross-entropy baselineViT-S/16 · ImageNet-Rerror rate: 70.3 -> 67.1Improved
Train with AENIB rather than the cross-entropy baselineViT-S/16 · Background Challenge Only-BG-Terror rate: 20.3 -> 17.8Improved
Add nuisance likelihood to the Dirichlet novelty score (ablation)AENIB · OBJECTS MNISTAUROC: 90.53 -> 92.43Improved
Add nuisance likelihood to the Dirichlet novelty score (ablation)AENIB · OBJECTS TextureAUROC: 75.04 -> 88.91Improved
Replace NMSE reconstruction loss with D2^2 (ablation)AENIB ViT-S/4 · CIFAR-10-Caverage corruption error rate: 13.0 -> 12.3Improved
Replace NMSE reconstruction loss with D2^2 (ablation)AENIB ViT-S/4 · CIFAR-100-Caverage corruption error rate: 36.9 -> 35.8Improved
Increase the information-bottleneck coefficient beta (ablation)AENIB ResNet-18 · CIFAR-10-Ccorruption errorHurt
Remove the reconstruction loss (ablation)AENIB ResNet-18 · CIFAR-10-Ccorruption errorHurt
Add the reconstruction loss (ablation)AENIB ResNet-18 · CIFAR-10accuracyImproved
Remove the nuisance loss (ablation)AENIB ResNet-18 · CIFAR-10accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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