Adversarial Learning

Adversarial learning aims to identify weaknesses in machine learning models. The goal is to identify potential problems that cannot be found using traditional evaluation using test sets. It has been used successfully in a wide range of applications, typically focused on a specific model or domain. In image classification, methods have been developed to fool models that recognize traffic signs by rather simple modifications of pictures. Another direction of adversarial learning aims to identify examples that could break or improve the training of the model if that example would be added to the training.


Chang, Luke; Dost, Katharina; Zhai, Kaiqi; Demontis, Ambra; Roli, Fabio; Dobbie, Gillian; Wicker, Jörg

Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning Journal Article

arxiv, 2105.00495 , 2021, (preprint).

Abstract | Links | BibTeX


Wicker, Jörg; Kramer, Stefan

The Best Privacy Defense is a Good Privacy Offense: Obfuscating a Search Engine User's Profile Journal Article

Data Mining and Knowledge Discovery, 31 (5), pp. 1419-1443, 2017, ISSN: 1573-756X.

Abstract | Links | BibTeX | Altmetric