AI Paper Atlas

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

Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers

Stefano Melacci, Gabriele Ciravegna, Angelo Sotgiu, Ambra Demontis, Battista Biggio, Marco Gori, Fabio Roli

TPAMI 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 33 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
add domain-knowledge constraint loss (+C) during training (ablation)FT · CIFAR-100 cleanF1 (%): 59.3 -> 64.0Improved
add domain-knowledge constraint loss (+C) (ablation)TL · CIFAR-100 cleanF1 (%): 52.0 -> 55.1Improved
add domain-knowledge constraint loss (+C) (ablation)TL · ANIMALS cleanF1 (%): 98.3 -> 98.6Improved
use strongly constrained training (+CC) instead of +C (ablation)TL · PASCAL-Part cleanF1 (%): 70.0 -> 69.4Hurt
add knowledge constraints (+C) against white-box MKA (ablation)FT · ANIMALS (eps=0.5)quality under attack (%): 25.6 -> 31.7Improved
add knowledge constraints (+C) against black-box MKA (ablation)FT · ANIMALS (eps=0.5)quality under attack (%): 51.2 -> 76.7Improved
add knowledge-based rejection (Rej) (ablation)FT · ANIMALS white-box MKAquality under attack (%): 25.6 -> 39.3Improved
combine constraints and rejection (+C with Rej) (ablation)FT · ANIMALS white-box MKAquality under attack (%): 25.6 -> 60.7Improved
add knowledge-based rejection (Rej) (ablation)FT · CIFAR-100 white-box MKAquality under attack (%): 29.0 -> 31.1Improved
add knowledge-based rejection (Rej) (ablation)FT · ANIMALS clean (eps=0)quality (%): 98.6 -> 92.7Hurt
use knowledge-based rejection with constrained model instead of Neural Rejection (ablation)FT · ANIMALS white-box MKAquality under attack (%): 37.3 -> 60.7Improved
use knowledge-based rejection instead of Neural Rejection on unconstrained model (ablation)TL · ANIMALS white-box MKAquality under attack (%): 55.5 -> 49.8Hurt

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