Deutsch Intern
  • none
Institute of Mathematics

Oberseminar "Mathematik des Maschinellen Lernens und Angewandte Analysis" - Atell Yehor Krasnopolsky

Explaining the Sensitivity Map Sparsity in Adversarially Trained Models
Date: 07/01/2026, 2:15 PM - 3:15 PM
Category: event
Location: Hubland Nord, Geb. 40, 01.003
Organizer: Lehrstuhl für Mathematik III (Maschinelles Lernen)
Speaker: Atell Yehor Krasnopolsky, Universität Würzburg

Sensitivity maps are gradient-based explainability tools used in machine learning to visualise the parts of the input most influential to a model’s decision-making. Training a model to be robust against slight perturbations of the input (adversarial training) has an effect on its sensitivity maps: they become sparser. The goal of my thesis was to mathematically answer the question: why is this the case? In this talk I will share the results.

 

Back