Alexander Warnecke (TU Braunschweig), Lukas Pirch (TU Braunschweig), Christian Wressnegger (Karlsruhe Institute of Technology (KIT)), Konrad Rieck (TU Braunschweig)

Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose the first method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.

View More Papers

CHKPLUG: Checking GDPR Compliance of WordPress Plugins via Cross-language...

Faysal Hossain Shezan (University of Virginia), Zihao Su (University of Virginia), Mingqing Kang (Johns Hopkins University), Nicholas Phair (University of Virginia), Patrick William Thomas (University of Virginia), Michelangelo van Dam (in2it), Yinzhi Cao (Johns Hopkins University), Yuan Tian (UCLA)

Read More

Cryptographic Oracle-based Conditional Payments

Varun Madathil (North Carolina State University), Sri Aravinda Krishnan Thyagarajan (NTT Research), Dimitrios Vasilopoulos (IMDEA Software Institute), Lloyd Fournier (None), Giulio Malavolta (Max Planck Institute for Security and Privacy), Pedro Moreno-Sanchez (IMDEA Software Institute)

Read More

DiffCSP: Finding Browser Bugs in Content Security Policy Enforcement...

Seongil Wi (KAIST), Trung Tin Nguyen (CISPA Helmholtz Center for Information Security, Saarland University), Jihwan Kim (KAIST), Ben Stock (CISPA Helmholtz Center for Information Security), Sooel Son (KAIST)

Read More