About me
Mark Niklas Müller is a PostDoc at the Secure, Reliable, and Intelligent Systems Lab of ETH Zürich and advised by Prof. Martin Vechev. Mark’s research focuses on provable guarantees for machine learning models. This includes both deterministic and probabilistic certification methods for a diverse range of architectures and certified training methods. He has led the research on these topics at SRI Lab for the last two years, including two industry collaborations, co-organized the Verification of Neural Networks Competition 2022 (VNN-Comp’22), and was the lead organizer for the 2nd Workshop on Formal Verification of Machine Learning (WFVML'23) at ICML’23 this year. More recently, he has been working on decoding and contamination detection for LLMs.
Education
- ETH Zurich, January 2020 - April 2024 Doctoral Student in the Department of Computer Science
- ETH Zurich, September 2019 - October 2020 Visiting Student in the Department of Computer Science
- University of Stuttgart, October 2018 - October 2020 M.Sc. in Aerospace Engineering
- University of Stuttgart, October 2014 - April 2018 B.Sc. in Aerospace Engineering
Best Master's degree in Aerospace Engineering
Best Bachelor's degree in Aerospace Engineering
Publications
2024
ConStat: Performance-Based Contamination Detection in Large Language Models
Jasper Dekoninck, Mark Niklas Müller, Martin Vechev
NeurIPS
2024
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin Vechev
NeurIPS
2024
Prompt Sketching for Large Language Models
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICML
2024
DAGER: Exact Gradient Inversion for Large Language Models
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
ArXiv
2024
Understanding Certified Training with Interval Bound Propagation
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICLR
2024
Expressivity of ReLU-Networks under Convex Relaxations
Maximilian Baader*, Mark Niklas Müller*, Yuhao Mao, Martin Vechev
ICLR
2024
* Equal contribution
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
ArXiv
2024
Overcoming the Paradox of Certified Training with Gaussian Smoothing
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
arXiv
2024
Evading Data Contamination Detection for Language Models is (too) Easy
Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev
arXiv
2024
2023
Automated Classification of Model Errors on ImageNet
Momchil Peychev*, Mark Niklas Müller*, Marc Fischer, Martin Vechev
NeurIPS
2023
* Equal contribution
Connecting Certified and Adversarial Training
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
NeuIPS
2023
Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
PLDI
2023
Efficient Certified Training and Robustness Verification of Neural ODEs
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICLR
2023
Certified Training: Small Boxes are All You Need
Mark Niklas Müller*, Franziska Eckert*, Marc Fischer, Martin Vechev
ICLR
2023
* Equal contribution
Spotlight
Spotlight
First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)
Christopher Brix, Mark Niklas Müller, Stanley Bak, Changliu Liu, Taylor T. Johnson
STTT ExPLAIn
2023
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
arXiv
2022
* Equal contribution
(De-)Randomized Smoothing for Decision Stump Ensembles
Miklós Z. Horváth*, Mark Niklas Müller*, Marc Fischer, Martin Vechev
NeurIPS
2022
* Equal contribution
Robust and Accurate - Compositional Architectures for Randomized Smoothing
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin Vechev
SRML@ICLR
2022
Boosting Randomized Smoothing with Variance Reduced Classifiers
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICLR
2022
Spotlight
Spotlight
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanović, Martin Vechev
ICLR
2022
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations
Mark Niklas Müller*, Gleb Makarchuk*, Gagandeep Singh, Markus Püschel, Martin Vechev
POPL
2022
* Equal contribution
2021
Certify or Predict: Boosting Certified Robustness with Compositional Architectures
Mark Niklas Müller, Mislav Balunović, Martin Vechev
ICLR
2021
Invited Talks and Academic Service
- Head Organizer of the 2nd Workshop on Formal Verification of Machine Learning WFVML'23@ICML (Honolulu, United States)
- Invited Talk at MobiliT.Ai 2023 - Realistic Neural Networks with Robustness Guarantees (Toulouse, France)
- Invited Talk at RPL@KTH - Realistic Neural Networks with Guarantees (Stockholm, Sweden)
- Invited Talk at LMML@FLoC - Verification of Realistic Neural Networks (Haifa, Israel)
- Co-Organizer of the 3rd International Verification of Neural Networks Competition, VNN-COMP'22 (Haifa, Israel)
- Invited Talk at the Workshop on Robust Artificial Intelligence - Scalable and Precise Certification of Neural Networks (online)
- Reviewer for: JMLR, NeurIPS'23, ICLR'24, TSRML@NeurIPS'22, WFVML@ICML'22
Supervised students
- M.Sc. - Simone Barbaro, Out of Distribution Detection via Calibrated Confidence
- M.Sc. - Claudio Ferrari, Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound [ICLR'2022]
- RCS - Ahmed Bouhoula, Branching Strategies for Multi-Neuron-Constraint-Based Bounding
- RCS - Miklós Z. Horváth, Boosting Randomized Smoothing with Variance Reduced Classifiers [ICLR'2022 (Spotlight)]
- RCS - Miklós Z. Horváth, Robust and Accurate -- Compositional Architectures for Randomized Smoothings [SRML@ICLR'2022]
- M.Sc. - Miklós Z. Horváth, (De-)Randomized Smoothing for Decision Stump Ensembles [NeurIPS'2022]
- M.Sc. - Franziska Eckert, Certified Training: Small Boxes are All You Need [ICLR'2023 (Spotlight)]
- M.Sc. - Mustafa Zeqiri, Efficient Robustness Verification of Neural Ordinary Differential Equations [ICLR'2023]
- PW - Yuhao Mao, Connecting Certified and Adversarial Training [NeurIPS'2023]
- M.Sc. - Robert Szasz, Focusing on Important Samples in Certified Training
- M.Sc. - Abra Ganz, Fine-tuning for Randomised Smoothing
- M.Sc. - Yuhao Mao, Understanding Certified Training with Interval Bound Propagation [arXiv]
Teaching
- Reliable and Trustworthy Artificial Intelligence - Fall 2023 - Course TA
- Rigorous Software Engineering - Spring 2023 - Head TA
- Deep Learning for Big Code - Spring 2023 - Course TA
- Reliable and Trustworthy Artificial Intelligence - Fall 2022 - Course TA
- Rigorous Software Engineering - Spring 2022 - Course TA
- Deep Learning for Big Code - Spring 2022 - Course TA
- Reliable and Trustworthy Artificial Intelligence - Fall 2021 - Course TA
- Rigorous Software Engineering - Spring 2021 - Course TA
- Deep Learning for Big Code - Spring 2021 - Course TA
Work experience
- G-Research, London, UK, 06/2023 - 09/2023 Quantitative Research Summer Intern
- Dr. Ing. h.c. F. Porsche AG, Weissach, DE, 11/2018 - 08/2019 Working Student
- Bosch Rexroth AG, Stuttgart, DE, 09/2018 - 10/2018 Data Science Intern
- Mercedes-AMG Petronas Formula One Team, Brackley, UK, 07/2017 - 07/2018 Industrial Placement - Aerodynamicist
Awards
- LRT Award for the best overall Master degree in Aerospace Engineering
- AIRBUS Defence & Space Award for the best overall Bachelor degree in Aerospace Engineering