Dr. Maximilian Baader

Post-Doc

mbaader@inf.ethz.ch
CAB H 81.1

Publications

2025

BaxBench: Can LLMs Generate Secure and Correct Backends?
Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev
ICML 2025 Spotlight

Website
Paper
Code
A Unified Approach to Routing and Cascading for LLMs
Jasper Dekoninck, Maximilian Baader, Martin Vechev
ICML 2025

Paper
Code
Ward: Provable RAG Dataset Inference via LLM Watermarks
Nikola Jovanović, Robin Staab, Maximilian Baader, Martin Vechev
ICLR 2025

Paper
Code
GRAIN: Exact Graph Reconstruction from Gradients
Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar I. Dimitrov, Martin Vechev
ICLR 2025

Paper
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
Jasper Dekoninck, Maximilian Baader, Martin Vechev
ICLR 2025

Paper
Code

2024

DAGER: Exact Gradient Inversion for Large Language Models
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
NeurIPS 2024

Poster
Slides
Paper
Code
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
NeurIPS 2024

Poster
Slides
Paper
Expressivity of ReLU-Networks under Convex Relaxations
Maximilian Baader*, Mark Niklas Müller*, Yuhao Mao, Martin Vechev
ICLR 2024 * Equal contribution

Paper
Overcoming the Paradox of Certified Training with Gaussian Smoothing
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
arXiv 2024

Paper
Evading Data Contamination Detection for Language Models is (too) Easy
Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev
arXiv 2024

Paper
Code

2023

Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation
Benjamin Bichsel, Anouk Paradis, Maximilian Baader, Martin Vechev
Quantum Journal 2023

Paper
Code

2022

Latent Space Smoothing for Individually Fair Representations
Momchil Peychev, Anian Ruoss, Mislav Balunović, Maximilian Baader, Martin Vechev
ECCV 2022

Poster
Slides
Paper
Code
On the Paradox of Certified Training
Nikola Jovanović*, Mislav Balunović*, Maximilian Baader, Martin Vechev
TMLR 2022 * Equal contribution

Blog
Paper
Code
The Fundamental Limits of Neural Networks for Interval Certified Robustness
Matthew Mirman, Maximilian Baader, Martin Vechev
TMLR 2022

Paper

2021

Scalable Certified Segmentation via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
ICML 2021

Poster
Paper
Fast and Precise Certification of Transformers
Gregory Bonaert, Dimitar I. Dimitrov, Maximilian Baader, Martin Vechev
PLDI 2021

Slides
Paper
Code
Efficient Certification of Spatial Robustness
Anian Ruoss, Maximilian Baader, Mislav Balunović, Martin Vechev
AAAI 2021

Paper

2020

Certified Defense to Image Transformations via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
NeurIPS 2020

Poster
Paper
Silq: A High-Level Quantum Language with Safe Uncomputation and Intuitive Semantics
Benjamin Bichsel, Maximilian Baader, Timon Gehr, Martin Vechev
PLDI 2020

Paper
Code
Universal Approximation with Certified Networks
Maximilian Baader, Matthew Mirman, Martin Vechev
ICLR 2020

Slides
Paper

2019

Certifying Geometric Robustness of Neural Networks
Mislav Balunović, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev
NeurIPS 2019

Poster
Paper

Education

  • ETH Zurich, 2018 -
    PhD Candidate in Computer Science
  • ETH Zurich , 2016 - 2018
    Masters in Physics
  • ETH Zurich, 2012 - 2016
    Bachelors in Physics

Teaching

  • Linear Algebra 2
    Spring 2018
  • Complex Analysis
    Autumn 2017
  • Linear Algebra 2
    Spring 2017
  • Complex Analysis
    Autumn 2016
  • Linear Algebra 2
    Spring 2016
  • Complex Analysis
    Autumn 2015