D3.5 Technical options and interventions report.pdf (1.48 MB)

D3.5 Technical options and interventions report (Full report)

Version 2 2021-02-09, 18:31

Version 1 2020-11-04, 13:05

online resource

posted on 2021-02-09, 18:31 authored by Samuel MarchalSamuel Marchal, Setareh Roshan, Alexey KirichenkoAlexey Kirichenko, Doris SchroederDoris Schroeder, Bernd StahlBernd Stahl

This report presents the second part of the study of model poisoning attacks on models from a popular class of anomaly detection algorithms, focusing on attack mitigation approaches.

Funding

This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme Under Grant Agreement no. 786641

History

Usage metrics

Keywords

Data poisoning attacks model poisoning attacks anomaly detection online distributed learning federated learning statistical distribution models with thresholds backdoor poisoning attacks poisoned input detection robust aggregation elliptic envelope Technology not elsewhere classified

Licence

CC BY 4.0

Exports

RefWorks

BibTeX

Ref. manager

Endnote

DataCite

NLM

DC