Voracek, Vaclav

10 publications

ICML 2025 An Interpretable N-Gram Perplexity Threat Model for Large Language Model Jailbreaks Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping

NeurIPS 2025 STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals Vaclav Voracek, Francesco Orabona

NeurIPSW 2024 A Realistic Threat Model for Large Language Model Jailbreaks Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping

ICML 2024 Convergence of Some Convex Message Passing Algorithms to a Fixed Point Vaclav Voracek, Tomas Werner

ALT 2024 Tight Bounds for Local Glivenko-Cantelli Moïse Blanchard, Vaclav Voracek

NeurIPS 2024 Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness Václav Voráček

ICML 2023 Improving L1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints Vaclav Voracek, Matthias Hein

JMLR 2023 Optimal Strategies for Reject Option Classifiers Vojtech Franc, Daniel Prusa, Vaclav Voracek

ICLR 2023 Sound Randomized Smoothing in Floating-Point Arithmetic Vaclav Voracek, Matthias Hein

ICML 2022 Provably Adversarially Robust Nearest Prototype Classifiers Václav Voráček, Matthias Hein