QR kȏd

Triple Down on Robustness: Understanding the Impact of Adversarial Triplet Compositions on Adversarial Robustness

Adversarial training, a widely used technique for fortifying the robustness of machine learning models, has seen its effectiveness further bolstered by modifying loss functions or incorporating additional terms into the training objective. While these adaptations are validated through empirical stud...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Glavni autori: Sander Joos, Tim Van hamme, Willem Verheyen, Davy Preuveneers, Wouter Joosen
Format: Artigo
Jezik:Inglês
Izdano: MDPI AG 2025-02-01
Serija:Machine Learning and Knowledge Extraction
Teme:
Online pristup:https://www.mdpi.com/2504-4990/7/1/14
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!