Explicit Defense Actions Against Test-Set Attacks

Authors: Scott Alfeld, Xiaojin Zhu, Paul Barford

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Using these methods, we perform an empirical investigation of optimal defense actions for a particular class of linear models autoregressive forecasters and find that for ten real world futures markets, the optimal defense action reduces the Bob s loss by between 78 and 97%.
Researcher Affiliation Collaboration Scott Alfeld, Xiaojin Zhu, Paul Barford Department of Computer Sciences University of Wisconsin Madison Madison WI 53706, USA com Score, Inc. 11950 Democracy Drive, Suite 600 Reston, VA 20190, USA.
Pseudocode No The paper does not contain explicitly labeled
Open Source Code No The paper does not provide an explicit statement about open-source code availability or a link to a repository.
Open Datasets Yes Data is freely available from www.quandl.com. Identification codes for individual datasets are provided in Figure 1.
Dataset Splits No The paper does not explicitly state training/validation/test dataset splits. It mentions
Hardware Specification No The paper mentions that
Software Dependencies Yes All figures were made with Matplotlib (Hunter 2007) v 1.5.1.
Experiment Setup No The paper mentions specific experimental settings like