# Disrupting Model Training with Adversarial Shortcuts

Source: [Disrupting Model Training with Adversarial Shortcuts](<https://www.sota2.com/research/paper/68fa6a471e209131cea2747e>)

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

Data updated: 2025-10-25T23:21:36.715Z

Authors: Ivan Evtimov, Ian Covert, Aditya Kusupati, Tadayoshi Kohno

Published: 2021-06-12T01:04:41.000Z

## Abstract

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we present a proof-of-concept approach for the image classification setting. We propose methods based on the notion of adversarial shortcuts, which encourage models to rely on non-robust signals rather than semantic features, and our experiments demonstrate that these measures successfully prevent deep learning models from achieving high accuracy on real, unmodified data examples.

## 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/2106.06654>)

[PDF](<https://arxiv.org/pdf/2106.06654.pdf>)