26 citations · 72 across the 18 of their papers we have counts for
3 papers · 1 filter
Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman
Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only again…
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman
A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data…
Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention
Yu Yang, Seungbae Kim, Jungseock Joo
Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic exp…