Mark Niklas Müller

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 36

Top Topics

Top Venues

Proc. ACM Program. Lang.

Publications

Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
DAGER: Exact Gradient Inversion for Large Language Models. CoRR (2024)
Philip Sosnin, Mark Niklas Müller, Maximilian Baader, Calvin Tsay, Matthew Wicker
Certified Robustness to Data Poisoning in Gradient-Based Training. CoRR (2024)
Jasper Dekoninck, Mark Niklas Müller, Martin T. Vechev
ConStat: Performance-Based Contamination Detection in Large Language Models. CoRR (2024)
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Automated Classification of Model Errors on ImageNet. CoRR (2024)
Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin T. Vechev
Evading Data Contamination Detection for Language Models is (too) Easy. CoRR (2024)
Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev
Expressivity of ReLU-Networks under Convex Relaxations. ICLR (2024)
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
SPEAR: Exact Gradient Inversion of Batches in Federated Learning. CoRR (2024)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Understanding Certified Training with Interval Bound Propagation. ICLR (2024)
Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang, Martin T. Vechev, Kristina Toutanova
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging. CoRR (2024)
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin T. Vechev
Overcoming the Paradox of Certified Training with Gaussian Smoothing. CoRR (2024)
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev
Code Agents are State of the Art Software Testers. CoRR (2024)
Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu
First Three Years of the International Verification of Neural Networks Competition (VNN-COMP). CoRR (2023)
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
Certified Training: Small Boxes are All You Need. ICLR (2023)
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Automated Classification of Model Errors on ImageNet. NeurIPS (2023)
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Prompt Sketching for Large Language Models. CoRR (2023)
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Efficient Certified Training and Robustness Verification of Neural ODEs. ICLR (2023)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Understanding Certified Training with Interval Bound Propagation. CoRR (2023)
Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev
Expressivity of ReLU-Networks under Convex Relaxations. CoRR (2023)
Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu
First three years of the international verification of neural networks competition (VNN-COMP). Int. J. Softw. Tools Technol. Transf. 25 (3) (2023)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
TAPS: Connecting Certified and Adversarial Training. CoRR (2023)
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Efficient Certified Training and Robustness Verification of Neural ODEs. CoRR (2023)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Connecting Certified and Adversarial Training. NeurIPS (2023)
Mark Niklas Müller, Marc Fischer, Robin Staab, Martin T. Vechev
Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks. Proc. ACM Program. Lang. 7 (PLDI) (2023)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
(De-)Randomized Smoothing for Decision Stump Ensembles. CoRR (2022)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Boosting Randomized Smoothing with Variance Reduced Classifiers. ICLR (2022)
Mark Niklas Müller, Christopher Brix, Stanley Bak, Changliu Liu, Taylor T. Johnson
The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results. CoRR (2022)
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound. CoRR (2022)
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. ACM Program. Lang. 6 (POPL) (2022)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
(De-)Randomized Smoothing for Decision Stump Ensembles. NeurIPS (2022)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Robust and Accurate - Compositional Architectures for Randomized Smoothing. CoRR (2022)
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound. ICLR (2022)
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
Certified Training: Small Boxes are All You Need. CoRR (2022)
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
Precise Multi-Neuron Abstractions for Neural Network Certification. CoRR (2021)
Mark Niklas Müller, Mislav Balunovic, Martin T. Vechev
Certify or Predict: Boosting Certified Robustness with Compositional Architectures. ICLR (2021)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Boosting Randomized Smoothing with Variance Reduced Classifiers. CoRR (2021)
Mark Niklas Müller, Robin Staab, Marc Fischer, Martin T. Vechev
Effective Certification of Monotone Deep Equilibrium Models. CoRR (2021)