vix.ing · top · new · best · stats · spec

Disrupting Model Training with Adversarial Shortcuts

2021/06/12 by Ivan Evtimov, Ian Covert, Evtimov, Ivan +5
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Nuclear reactor physics and engineering

paper · pdf · doi:10.48550/arxiv.2106.06654

openalex publication_date 2021/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

Related