Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers

no code implementations • 22 Sep 2021 • Honggang Yu, Shihfeng Zeng, Teng Zhang, Ing-Chao Lin, Yier Jin

As a result, our theoretical proofs provide support to more efficient active learning methods with the help of adversarial examples, contrary to previous works where adversarial examples are often used as destructive solutions.

Active Learning Adversarial Attack +1