# Efficiently Attacking Memorization Scores

Source: [Efficiently Attacking Memorization Scores](<https://www.sota2.com/research/paper/68fa7ba51e209131cea89984>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T07:03:33.600Z

Authors: Tue Do, Varun Chandrasekaran, Daniel Alabi

Published: 2025-09-24T18:33:10.000Z

## Abstract

Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning raise the question: can these scores themselves be adversarially manipulated? In this work, we present a systematic study of the feasibility of attacking memorization-based influence estimators. We characterize attacks for producing highly memorized samples as highly sensitive queries in the regime where a trained algorithm is accurate. Our attack (calculating the pseudoinverse of the input) is practical, requiring only black-box access to model outputs and incur modest computational overhead. We empirically validate our attack across a wide suite of image classification tasks, showing that even state-of-the-art proxies are vulnerable to targeted score manipulations. In addition, we provide a theoretical analysis of the stability of memorization scores under adversarial perturbations, revealing conditions under which influence estimates are inherently fragile. Our findings highlight critical vulnerabilities in influence-based attribution and suggest the need for robust defenses. All code can be found at https://github.com/tuedo2/MemAttack

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.20463>)

[PDF](<https://arxiv.org/pdf/2509.20463.pdf>)
