Æȷοì
Mark Niklas Müller
Mark Niklas Müller
PhD Student, ETH Zurich
inf.ethz.chÀÇ À̸ÞÀÏ È®ÀÎµÊ - ȨÆäÀÌÁö
Á¦¸ñ
Àοë
Àοë
¿¬µµ
PRIMA: general and precise neural network certification via scalable convex hull approximations
MN Müller, G Makarchuk, G Singh, M Püschel, M Vechev
Proceedings of the ACM on Programming Languages 6 (POPL), 1-33, 2022
109*2022
Complete verification via multi-neuron relaxation guided branch-and-bound
C Ferrari, MN Muller, N Jovanovic, M Vechev
The Tenth International Conference on Learning Representations, 2022 (ICLR'22), 2022
662022
The third international verification of neural networks competition (vnn-comp 2022): Summary and results
MN Müller, C Brix, S Bak, C Liu, TT Johnson
arXiv preprint arXiv:2212.10376, 2022
382022
First three years of the international verification of neural networks competition (VNN-COMP)
C Brix, MN Müller, S Bak, TT Johnson, C Liu
International Journal on Software Tools for Technology Transfer 25 (3), 329-339, 2023
372023
Boosting randomized smoothing with variance reduced classifiers
MZ Horváth, MN Müller, M Fischer, M Vechev
The Tenth International Conference on Learning Representations, 2022 (ICLR'22), 2021
332021
Certified training: Small boxes are all you need
MN Müller, F Eckert, M Fischer, M Vechev
The Eleventh International Conference on Learning Representations (ICLR'23), 2022
252022
Certify or predict: Boosting certified robustness with compositional architectures
MN Müller, M Balunović, M Vechev
The Ninth International Conference on Learning Representations, 2021 (ICLR'21), 2021
142021
Taps: Connecting certified and adversarial training
Y Mao, MN Müller, M Fischer, M Vechev
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS'23), 2023
8*2023
Robust and Accurate--Compositional Architectures for Randomized Smoothing
MZ Horváth, MN Müller, M Fischer, M Vechev
arXiv preprint arXiv:2204.00487, 2022
82022
Abstract interpretation of fixpoint iterators with applications to neural networks
MN Müller, M Fischer, R Staab, M Vechev
Proceedings of the ACM on Programming Languages 7 (PLDI), 786-810, 2023
7*2023
The third international verification of neural networks competition (VNN-COMP 2022): Summary and results. CoRR abs/2212.10376 (2022)
MN Müller, C Brix, S Bak, C Liu, TT Johnson
arXiv preprint arXiv:2212.10376, 2022
52022
Understanding certified training with interval bound propagation
Y Mao, MN Müller, M Fischer, M Vechev
arXiv preprint arXiv:2306.10426, 2023
22023
Evading Data Contamination Detection for Language Models is (too) Easy
J Dekoninck, MN Müller, M Baader, M Fischer, M Vechev
arXiv preprint arXiv:2402.02823, 2024
12024
Automated Classification of Model Errors on ImageNet
M Peychev, MN Mueller, M Fischer, M Vechev
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS'23), 2023
12023
Efficient Certified Training and Robustness Verification of Neural ODEs
M Zeqiri, MN Müller, M Fischer, M Vechev
The Eleventh International Conference on Learning Representations (ICLR'23), 2023
1*2023
(De-) Randomized Smoothing for Decision Stump Ensembles
M Horváth, M Müller, M Fischer, M Vechev
Advances in Neural Information Processing Systems 35, 3066-3081, 2022
12022
Overcoming the Paradox of Certified Training with Gaussian Smoothing
S Balauca, MN Müller, Y Mao, M Baader, M Fischer, M Vechev
arXiv preprint arXiv:2403.07095, 2024
2024
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
DI Dimitrov, M Baader, MN Müller, M Vechev
arXiv preprint arXiv:2403.03945, 2024
2024
Prompt Sketching for Large Language Models
L Beurer-Kellner, MN Müller, M Fischer, M Vechev
arXiv preprint arXiv:2311.04954, 2023
2023
Expressivity of ReLU-Networks under Convex Relaxations
M Baader, MN Müller, Y Mao, M Vechev
arXiv preprint arXiv:2311.04015, 2023
2023
ÇöÀç ½Ã½ºÅÛÀÌ ÀÛµ¿µÇÁö ¾Ê½À´Ï´Ù. ³ªÁß¿¡ ´Ù½Ã ½ÃµµÇØ ÁÖ¼¼¿ä.
ÇмúÀÚ·á 1–20