Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Elre T. Oldewage, John Bronskill, Richard E. Turner. Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners. In Javier Antorán, Arno Blaas, Fan Feng, Sahra Ghalebikesabi, Ian Mason, Melanie F. Pradier, David Rohde, Francisco J. R. Ruiz, Aaron Schein, editors, Proceedings on "I Can't Believe It's Not Better! - Understanding Deep Learning Through Empirical Falsification" at NeurIPS 2022 Workshops, 03 December 2022, New Orleans, Louisiana, USA. Volume 187 of Proceedings of Machine Learning Research, pages 27-40, PMLR, 2022. [doi]

This author has not been identified. Look up 'Elre T. Oldewage' in GoogleThis author has not been identified. Look up 'John Bronskill' in GoogleThis author has not been identified. Look up 'Richard E. Turner' in Google

runs on WebDSL