Klas Leino
9 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (15) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5)
π
Cross-Pollinator
(8)
π
Renaissance Researcher
(5)
π
Triple Crown
π₯
Unstoppable
(6)
Conferences
ICLR (5)
NIPS (2)
ACL (1)
ICML (1)
Top co-authors
Keywords
adversarial example
(2)
adversarial robustness
(2)
certified robustness
(2)
gradient descent
(1)
recurrent neural network
(1)
language model
(1)
robustness certification
(1)
lipschitz constant
(1)
neural network verification
(1)
global robustness
(1)
robust accuracy
(1)
residual network
(1)
causal analysis
(1)
syntactic structure
(1)
lstm language model
(1)
subject-verb agreement
(1)
certifiable robustness
(1)
lipschitz bound
(1)
provable robustness
(1)
certified accuracy
(1)
Papers
A Recipe for Improved Certifiable Robustness
ICLR 2024
Unlocking Deterministic Robustness Certification on ImageNet
NIPS 2023
On the Perils of Cascading Robust Classifiers
ICLR 2023
Selective Ensembles for Consistent Predictions
ICLR 2022
Globally-Robust Neural Networks
ICML 2021
Fast Geometric Projections for Local Robustness Certification
ICLR 2021
Relaxing Local Robustness
NIPS 2021
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
ACL 2020
Feature-Wise Bias Amplification
ICLR 2019