AI Paper Atlas

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

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates

Daniele Angioni, Luca Demetrio, Maura Pintor, Luca Oneto, Davide Anguita, Battista Biggio, Fabio Roli

TPAMI 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 19 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 the old model with a more robust new one (naive update)old CIFAR-10 robust model · CIFAR-10RNF rate: roughly 2% to 6%Hurt
fine-tune with PCT instead of naive replacementnaive update · CIFAR-10 (C3, C5)RNFs / robust error: RNFs 6.30 -> 26.10; robust error 40.65 -> 66.10Hurt
fine-tune with PCT instead of naive replacementnaive update · ImageNet (I4, I5)RNFs: 2.54 -> 37.22Hurt
add adversarial training to PCT (PCAT)PCT · CIFAR-10 (C3, C5)RNFs: 26.10 -> 10.95Improved
use RCAT instead of PCATPCAT · CIFAR-10 (C3, C5)RNFs: 10.95 -> 6.00Improved
use RCAT instead of naive replacementnaive update · CIFAR-10 meandelta RNFs: +0.18Improved
use RCAT instead of naive replacementnaive update · ImageNet meandelta NFs: +0.55Improved
use RCAT instead of naive replacementnaive update · CIFAR-10 meandelta robust error: -0.29No clear effect
use PCAT instead of naive replacementnaive update · ImageNet meandelta NFs: -0.17No clear effect
RCAT versus PCAT in sequential ImageNet updatesPCAT · ImageNet sequential (I4, I5)NFs: 3.32 -> 2.42Improved
RCAT versus PCT in sequential ImageNet updatesPCT · ImageNet sequential (I4, I5)RNFs: 27.22 -> 2.02Improved
RCAT versus PCAT on update (C2, C3)PCAT · CIFAR-10 (C2, C3)NFs + RNFs: RNFs 3.15 -> 5.05Hurt

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