AI Paper Atlas

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

Resilience of Entropy Model in Distributed Neural Networks

Milin Zhang, Mohammad Abdi, Shahriar Rifat, Francesco Restuccia

ECCV 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization · 1 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
apply object-aware total variation denoising to PGD-E attacked inputs (eps=16/255)ResNet-50 with MSHP entropy model · ImageNet PGD-E eps=16/255data size (KB): 18.79 -> 13.44Improved
apply object-aware TV denoising (eps=8/255 and 16/255)ResNet-50 with MSHP · ImageNet PGD-Eaccuracy (%): 52.13 -> 59.87 (eps=16/255); 65.62 -> 67.22 (eps=8/255)Improved
apply object-aware TV denoising on small perturbations (eps=2/255)ResNet-50 with MSHP · ImageNet PGD-E eps=2/255accuracy (%): 73.26 -> 70.82Hurt
apply defense against adaptive low-frequency and regional attacksResNet-50 with MSHP · ImageNet adaptive attacks eps=4/255data size (KB): 14.11 -> 9.56 (frequency); 14.05 -> 9.50 (regional)Improved
PGD-E entropy attack versus accuracy attack PGD-Accdistributed DNN with entropy model · ImageNet eps=4/255data size: PGD-E 1.35x bit rate, -2.34% accuracy; PGD-Acc +7.28% size, -42.88% accuracyMixed
add shot noise corruption (high-frequency)entropy-coded ResNet-50 · ImageNet-C severity 5data size: +65.31% on averageHurt
add defocus blur or contrast corruptionentropy-coded ResNet-50 · ImageNet-C severity 5data size: -53.31% and -67.45% on averageImproved
use MSHP instead of FP entropy model under PGD-E (eps=8/255)ResNet-50 · ImageNet eps=8/255data size increase under PGD-E: 21.93% (FP) vs 46.82% (MSHP) size increaseHurt
use mask on denoising to restrict to non-object area (ablation)TV denoising defense · ImageNetaccuracyImproved

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