3 papers
cs.LG2020
Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning
Guneet S. Dhillon, Nicholas Carlini
Stochastic Activation Pruning (SAP) (Dhillon et al., 2018) is a defense to adversarial examples that was attacked and found to be broken by the "Obfuscated Gradients" paper (Athaly…
cs.LG2019
A Baseline for Few-Shot Image Classification
Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran +1
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current sta…
cs.LG2018
Stochastic Activation Pruning for Robust Adversarial Defense
Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton +4
Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threa…