activity
20182021
most citedRelaxing Local Robustness

2 citations · 3 across the 2 of their papers we have counts for

collaborators

7 papers

cs.LG20212 cited

Relaxing Local Robustness

Klas Leino, Matt Fredrikson

Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep lear…

cs.LG2021

Globally-Robust Neural Networks

Klas Leino, Zifan Wang, Matt Fredrikson

The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We…

cs.CL20201 cited

Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models

Kaiji Lu, Piotr Mardziel, Klas Leino +2

LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs lear…

cs.LG2020

Fast Geometric Projections for Local Robustness Certification

Aymeric Fromherz, Klas Leino, Matt Fredrikson +2

Local robustness ensures that a model classifies all inputs within an -ball consistently, which precludes various forms of adversarial inputs. In this paper, we present a f…

cs.LG2019

Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference

Klas Leino, Matt Fredrikson

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we…

cs.LG2018

Feature-Wise Bias Amplification

Klas Leino, Emily Black, Matt Fredrikson +2

We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth.…