Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"Why do so?" -- A Practical Perspective on Machine Learning Security


Jul 11, 2022
Kathrin Grosse, Lukas Bieringer, Tarek Richard Besold, Battista Biggio, Katharina Krombholz

* under submission - 18 pages, 3 tables and 4 figures. Long version of the paper accepted at: New Frontiers of Adversarial Machine [email protected] 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning


May 04, 2022
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Sebastiano Vascon, Werner Zellinger, Bernhard A. Moser, Alina Oprea, Battista Biggio, Marcello Pelillo, Fabio Roli

* 35 pages, submitted to ACM 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Machine Learning Security against Data Poisoning: Are We There Yet?


Apr 12, 2022
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo

* preprint, 10 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions


Jun 14, 2021
Antonio Emanuele Cinà, Kathrin Grosse, Sebastiano Vascon, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo

* 21 pages, submitted to NeurIPS 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mental Models of Adversarial Machine Learning


May 08, 2021
Lukas Bieringer, Kathrin Grosse, Michael Backes, Katharina Krombholz

* 19 pages, 8 figures, under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarial Examples and Metrics


Jul 15, 2020
Nico Döttling, Kathrin Grosse, Michael Backes, Ian Molloy

* 25 pages, 1 figure, under submission, fixe typos from previous version 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A new measure for overfitting and its implications for backdooring of deep learning


Jun 18, 2020
Kathrin Grosse, Taesung Lee, Youngja Park, Michael Backes, Ian Molloy

* 11 pages, 10 figures, under submission, (updated contact information) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

How many winning tickets are there in one DNN?


Jun 12, 2020
Kathrin Grosse, Michael Backes

* 17 pages, 15 figures, under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarial Vulnerability Bounds for Gaussian Process Classification


Sep 19, 2019
Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A Alvarez

* 10 pages + 2 pages references + 7 pages of supplementary. 12 figures. Submitted to AAAI 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>