SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.06640 · 2022

Towards Adversarial Evaluations for Inexact Machine Unlearning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.06640")
get_code_for_paper("2201.06640")
have("2201.06640")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.06640.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.06640.svg)](https://syntology.ai/paper/2201.06640)

Connect an agent — have() is free.