Václav Voráček
8 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
Venues
Top co-authors
Research topics
Keywords
randomized smoothing
(3)
adversarial robustness
(3)
certified robustness
(2)
sample complexity
(1)
neural network optimization
(1)
statistical estimation
(1)
reject option
(1)
coordinate descent
(1)
selective classification
(1)
concentration inequality
(1)
distance metric
(1)
convergence rate
(1)
fixed point
(1)
image classifier
(1)
jailbreak attack
(1)
bayes classifier
(1)
confidence sequence
(1)
certified defense
(1)
randomized decision rule
(1)
n-gram language model
(1)
Papers
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
ICML 2025
Convergence of Some Convex Message Passing Algorithms to a Fixed Point
ICML 2024
Tight Bounds for Local Glivenko-Cantelli
ALT 2024
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
NeurIPS 2024
Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints
ICML 2023
Optimal Strategies for Reject Option Classifiers
JMLR 2023
Sound Randomized Smoothing in Floating-Point Arithmetic
ICLR 2023
Provably Adversarially Robust Nearest Prototype Classifiers
ICML 2022