Mark Niklas Müller

According to our database, Mark Niklas Müller authored at least 28 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Training and Certification of Neural Networks with Guarantees.

Mark Niklas Müller

PhD thesis, 2024

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging.

Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang, Martin T. Vechev, Kristina Toutanova

CoRR, 2024

Code Agents are State of the Art Software Testers.

Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev

CoRR, 2024

Certified Robustness to Data Poisoning in Gradient-Based Training.

Philip Sosnin, Mark Niklas Müller, Maximilian Baader, Calvin Tsay, Matthew Wicker

CoRR, 2024

ConStat: Performance-Based Contamination Detection in Large Language Models.

Jasper Dekoninck, Mark Niklas Müller, Martin T. Vechev

CoRR, 2024

DAGER: Exact Gradient Inversion for Large Language Models.

Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev

CoRR, 2024

Overcoming the Paradox of Certified Training with Gaussian Smoothing.

Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin T. Vechev

CoRR, 2024

SPEAR: Exact Gradient Inversion of Batches in Federated Learning.

Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev

CoRR, 2024

Evading Data Contamination Detection for Language Models is (too) Easy.

Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin T. Vechev

CoRR, 2024

Prompt Sketching for Large Language Models.

Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Understanding Certified Training with Interval Bound Propagation.

Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Expressivity of ReLU-Networks under Convex Relaxations.

Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

First three years of the international verification of neural networks competition (VNN-COMP).

Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu

Int. J. Softw. Tools Technol. Transf., June, 2023

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks.

Mark Niklas Müller, Marc Fischer, Robin Staab, Martin T. Vechev

Proc. ACM Program. Lang., 2023

TAPS: Connecting Certified and Adversarial Training.

Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

CoRR, 2023

Automated Classification of Model Errors on ImageNet.

Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Connecting Certified and Adversarial Training.

Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient Certified Training and Robustness Verification of Neural ODEs.

Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Certified Training: Small Boxes are All You Need.

Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

PRIMA: general and precise neural network certification via scalable convex hull approximations.

Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev

Proc. ACM Program. Lang., 2022

The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results.

Mark Niklas Müller, Christopher Brix, Stanley Bak, Changliu Liu, Taylor T. Johnson

CoRR, 2022

Robust and Accurate - Compositional Architectures for Randomized Smoothing.

Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

CoRR, 2022

(De-)Randomized Smoothing for Decision Stump Ensembles.

Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Boosting Randomized Smoothing with Variance Reduced Classifiers.

Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev

Proceedings of the Tenth International Conference on Learning Representations, 2022

Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound.

Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Effective Certification of Monotone Deep Equilibrium Models.

Mark Niklas Müller, Robin Staab, Marc Fischer, Martin T. Vechev

CoRR, 2021

Precise Multi-Neuron Abstractions for Neural Network Certification.

Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev

CoRR, 2021

Certify or Predict: Boosting Certified Robustness with Compositional Architectures.

Mark Niklas Müller, Mislav Balunovic, Martin T. Vechev

Proceedings of the 9th International Conference on Learning Representations, 2021