164 citations · 1.5k across the 78 of their papers we have counts for
21 papers · 1 filter
WITCHcraft: Efficient PGD attacks with random step size
Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum +4
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods wit…
Certified Data Removal from Machine Learning Models
Chuan Guo, Tom Goldstein, Awni Hannun +1
Good data stewardship requires removal of data at the request of the data's owner. This raises the question if and how a trained machine-learning model, which implicitly stores inf…
Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
Ali Shafahi, Amin Ghiasi, Furong Huang +1
Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. Th…
Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
Yogesh Balaji, Tom Goldstein, Judy Hoffman
Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversar…
Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
Zuxuan Wu, Ser-Nam Lim, Larry Davis +1
We present a systematic study of adversarial attacks on state-of-the-art object detection frameworks. Using standard detection datasets, we train patterns that suppress the objectn…
Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
Micah Goldblum, Liam Fowl, Tom Goldstein
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, fe…