Adversarial Learning

The objective of adversarial learning is to pinpoint vulnerabilities in machine learning models that traditional testing methods cannot detect. It has proven to be effective in various applications, often centered around a particular model or field. For instance, in image classification, techniques have been created to deceive models that identify traffic signs by making minor alterations to images. Another approach to adversarial learning seeks to recognize instances that could disrupt or enhance the model’s training if they were included in the training data.

2024

Kim, Jonathan; Urschler, Martin; Riddle, Pat; Wicker, Jörg

Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection Proceedings Article

In: Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pp. 90-97, 2024.

Abstract | Links | BibTeX

2023

Chang, Xinglong; Dost, Katharina; Dobbie, Gillian; Wicker, Jörg

Poison is Not Traceless: Fully-Agnostic Detection of Poisoning Attacks Unpublished Forthcoming

Forthcoming.

Abstract | Links | BibTeX

Chang, Xinglong; Dobbie, Gillian; Wicker, Jörg

Fast Adversarial Label-Flipping Attack on Tabular Data Unpublished Forthcoming

Forthcoming.

Abstract | Links | BibTeX

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

BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability Proceedings Article

In: Kashima, Hisashi; Ide, Tsuyoshi; Peng, Wen-Chih (Ed.): The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 3-14, Springer Nature Switzerland, Cham, 2023, ISSN: 978-3-031-33374-3.

Abstract | Links | BibTeX

Chen, Zeyu; Dost, Katharina; Zhu, Xuan; Chang, Xinglong; Dobbie, Gillian; Wicker, Jörg

Targeted Attacks on Time Series Forecasting Proceedings Article

In: Kashima, Hisashi; Ide, Tsuyoshi; Peng, Wen-Chih (Ed.): The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 314-327, Springer Nature Switzerland, Cham, 2023, ISSN: 978-3-031-33383-5.

Abstract | Links | BibTeX

2017

Wicker, Jörg; Kramer, Stefan

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

In: Data Mining and Knowledge Discovery, vol. 31, no. 5, pp. 1419-1443, 2017, ISSN: 1573-756X.

Abstract | Links | BibTeX