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

Fine-Grained Trackability in Protocol Executions

Ksenia Budykho (Surrey Centre for Cyber Security, University of Surrey, UK), Ioana Boureanu (Surrey Centre for Cyber Security, University of Surrey, UK), Steve Wesemeyer (Surrey Centre for Cyber Security, University of Surrey, UK), Daniel Romero (NCC Group), Matt Lewis (NCC Group), Yogaratnam Rahulan (5G/6G Innovation Centre - 5GIC/6GIC, University of Surrey, UK), Fortunat Rajaona (Surrey…

Read More

Do Not Give a Dog Bread Every Time He...

Chongqing Lei (Southeast University), Zhen Ling (Southeast University), Yue Zhang (Jinan University), Kai Dong (Southeast University), Kaizheng Liu (Southeast University), Junzhou Luo (Southeast University), Xinwen Fu (University of Massachusetts Lowell)

Read More

Human Drivers' Situation Awareness of Autonomous Driving Under Physical-world...

Katherine S. Zhang (Purdue University), Claire Chen (Pennsylvania State University), Aiping Xiong (Pennsylvania State University)

Read More

Private Certifier Intersection

Bishakh Chandra Ghosh (Indian Institute of Technology Kharagpur), Sikhar Patranabis (IBM Research - India), Dhinakaran Vinayagamurthy (IBM Research - India), Venkatraman Ramakrishna (IBM Research - India), Krishnasuri Narayanam (IBM Research - India), Sandip Chakraborty (Indian Institute of Technology Kharagpur)

Read More