1 code implementation • 1 Jun 2020 • Kyungmi Lee, Anantha P. Chandrakasan
We identify three common cases that lead to overestimation of adversarial accuracy against bounded first-order attack methods, which is popularly used as a proxy for adversarial robustness in empirical studies.
no code implementations • 18 Jul 2019 • Euntae Choi, Kyungmi Lee, Ki-Young Choi
Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting.