Search Results for author: Katharina Dost

Found 4 papers, 3 papers with code

Memento: Facilitating Effortless, Efficient, and Reliable ML Experiments

1 code implementation17 Apr 2023 Zac Pullar-Strecker, Xinglong Chang, Liam Brydon, Ioannis Ziogas, Katharina Dost, Jörg Wicker

Running complex sets of machine learning experiments is challenging and time-consuming due to the lack of a unified framework.

Management

Hitting the Target: Stopping Active Learning at the Cost-Based Optimum

1 code implementation7 Oct 2021 Zac Pullar-Strecker, Katharina Dost, Eibe Frank, Jörg Wicker

This work enables practitioners to employ active learning by providing actionable recommendations for which stopping criteria are best for a given real-world scenario.

Active Learning

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

1 code implementation2 May 2021 Xinglong Chang, Katharina Dost, Kaiqi Zhao, Ambra Demontis, Fabio Roli, Gill Dobbie, Jörg Wicker

Applicability Domain defines a domain based on the known compounds and rejects any unknown compound that falls outside the domain.

Blocking

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

no code implementations24 Oct 2023 Xinglong Chang, Katharina Dost, Gillian Dobbie, Jörg Wicker

This paper presents a novel fully-agnostic framework, DIVA (Detecting InVisible Attacks), that detects attacks solely relying on analyzing the potentially poisoned data set.

Cannot find the paper you are looking for? You can Submit a new open access paper.