Detecting Potential Local Adversarial Examples for Human-Interpretable Defense

September 07, 2018 ยท Declared Dead ยท ๐Ÿ› Nemesis/UrbReas/SoGood/IWAISe/GDM@PKDD/ECML

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki arXiv ID 1809.02397 Category stat.ML: Machine Learning (Stat) Cross-listed cs.CR, cs.LG Citations 5 Venue Nemesis/UrbReas/SoGood/IWAISe/GDM@PKDD/ECML Last Checked 4 months ago
Abstract
Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval. In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifier's decision, in order to control the provided information and avoid a fraud.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning (Stat)

๐Ÿ”ฎ ๐Ÿ”ฎ The Ethereal

Layer Normalization

Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton

stat.ML ๐Ÿ› arXiv ๐Ÿ“š 12.0K cites 9 years ago

Died the same way โ€” ๐Ÿ‘ป Ghosted