Project: safeai.ethz.ch
Safe Artificial Intelligence
Building safe and robust artifical intelligence systems.
Startups
The world's first platform for building and deploying Trustworthy AI.
Publications
2025
Type-Constrained Code Generation with Language Models
Niels Mündler†, Jingxuan He†, Hao Wang, Koushik Sen, Dawn Song, Martin Vechev
VerifAI, DL4C @ ICLR
2025
† Co-leadership
Ward: Provable RAG Dataset Inference via LLM Watermarks
Nikola Jovanović, Robin Staab, Maximilian Baader, Martin Vechev
ICLR
2025
Practical Attacks against Black-box Code Completion Engines
Slobodan Jenko*, Niels Mündler*, Jingxuan He, Mark Vero, Martin Vechev
Building Trust in LLMs, DL4C @ ICLR
2025
* Equal contribution
Towards Watermarking of Open-Source LLMs
Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
WMARK @ ICLR
2025
Black-Box Detection of Language Model Watermarks
Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICLR
2025
Discovering Clues of Spoofed LM Watermarks
Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
WMARK @ ICLR
2025
GRAIN: Exact Graph Reconstruction from Gradients
Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar I. Dimitrov, Martin Vechev
ICLR
2025
2024
Private Attribute Inference from Images with Vision-Language Models
Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev
NeurIPS
2024
DAGER: Exact Gradient Inversion for Large Language Models
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin Vechev
NeurIPS
2024
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Dimitar I. Dimitrov, Maximilian Baader, 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
CuTS: Customizable Tabular Synthetic Data Generation
Mark Vero, Mislav Balunović, Martin Vechev
ICML
2024
Watermark Stealing in Large Language Models
Nikola Jovanović, Robin Staab, Martin Vechev
ICML
2024
R2-FM@ICLR24 Oral
R2-FM@ICLR24 Oral
From Principle to Practice: Vertical Data Minimization for Machine Learning
Robin Staab, Nikola Jovanović, Mislav Balunović, Martin Vechev
IEEE S&P
2024
Back to the Drawing Board for Fair Representation Learning
Angéline Pouget, Nikola Jovanović, Mark Vero, Robin Staab, Martin Vechev
arXiv
2024
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Niels Mündler, Jingxuan He, Slobodan Jenko, Martin Vechev
ICLR
2024
Understanding Certified Training with Interval Bound Propagation
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICLR
2024
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev
ICLR
2024
Expressivity of ReLU-Networks under Convex Relaxations
Maximilian Baader*, Mark Niklas Müller*, Yuhao Mao, Martin Vechev
ICLR
2024
* Equal contribution
Overcoming the Paradox of Certified Training with Gaussian Smoothing
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, 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
Large Language Models for Code: Security Hardening and Adversarial Testing
Jingxuan He, Martin Vechev
ACM CCS
2023
Distinguished Paper Award
Distinguished Paper Award
TabLeak: Tabular Data Leakage in Federated Learning
Mark Vero, Mislav Balunović, Dimitar I. Dimitrov, Martin Vechev
ICML
2023
FARE: Provably Fair Representation Learning with Practical Certificates
Nikola Jovanović, Mislav Balunović, Dimitar I. Dimitrov, Martin Vechev
ICML
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
Human-Guided Fair Classification for Natural Language Processing
Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin Vechev
ICLR
2023
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
LAMP: Extracting Text from Gradients with Language Model Priors
Mislav Balunović*, Dimitar I. Dimitrov*, Nikola Jovanović, Martin Vechev
NeurIPS
2022
* Equal contribution
Private and Reliable Neural Network Inference
Nikola Jovanović, Marc Fischer, Samuel Steffen, Martin Vechev
ACM CCS
2022
Latent Space Smoothing for Individually Fair Representations
Momchil Peychev, Anian Ruoss, Mislav Balunović, Maximilian Baader, Martin Vechev
ECCV
2022
On the Paradox of Certified Training
Nikola Jovanović*, Mislav Balunović*, Maximilian Baader, Martin Vechev
TMLR
2022
* Equal contribution
Data Leakage in Federated Averaging
Dimitar I. Dimitrov, Mislav Balunović, Nikola Konstantinov, Martin Vechev
TMLR
2022
Shared Certificates for Neural Network Verification
Marc Fischer*, Christian Sprecher*, Dimitar I. Dimitrov, Gagandeep Singh, Martin Vechev
CAV
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
Provably Robust Adversarial Examples
Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev
ICLR
2022
Bayesian Framework for Gradient Leakage
Mislav Balunović, Dimitar I. Dimitrov, Robin Staab, 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
Automated Discovery of Adaptive Attacks on Adversarial Defenses
Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev
NeurIPS
2021
Robustness Certification for Point Cloud Models
Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev
ICCV
2021
Scalable Polyhedral Verification of Recurrent Neural Networks
Wonryong Ryou, Jiayu Chen, Mislav Balunović, Gagandeep Singh, Andrei Dan, Martin Vechev
CAV
2021
Scalable Certified Segmentation via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
ICML
2021
Automated Discovery of Adaptive Attacks on Adversarial Defenses
Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev
AutoML@ICML
2021
Oral
Oral
Fast and Precise Certification of Transformers
Gregory Bonaert, Dimitar I. Dimitrov, Maximilian Baader, Martin Vechev
PLDI
2021
Certify or Predict: Boosting Certified Robustness with Compositional Architectures
Mark Niklas Müller, Mislav Balunović, Martin Vechev
ICLR
2021
Scaling Polyhedral Neural Network Verification on GPUs
Christoph Müller*, François Serre*, Gagandeep Singh, Markus Püschel, Martin Vechev
MLSys
2021
* Equal contribution
Robustness Certification with Generative Models
Matthew Mirman, Alexander Hägele, Timon Gehr, Pavol Bielik, Martin Vechev
PLDI
2021
Efficient Certification of Spatial Robustness
Anian Ruoss, Maximilian Baader, Mislav Balunović, Martin Vechev
AAAI
2021
2020
Learning Certified Individually Fair Representations
Anian Ruoss, Mislav Balunović, Marc Fischer, Martin Vechev
NeurIPS
2020
Certified Defense to Image Transformations via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
NeurIPS
2020
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin Vechev
ICML
2020
Adversarial Training and Provable Defenses: Bridging the Gap
Mislav Balunović, Martin Vechev
ICLR
2020
Oral
Oral
Universal Approximation with Certified Networks
Maximilian Baader, Matthew Mirman, Martin Vechev
ICLR
2020
2019
Beyond the Single Neuron Convex Barrier for Neural Network Certification
Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin Vechev
NeurIPS
2019
Certifying Geometric Robustness of Neural Networks
Mislav Balunović, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev
NeurIPS
2019
Online Robustness Training for Deep Reinforcement Learning
Marc Fischer, Matthew Mirman, Steven Stalder, Martin Vechev
arXiv
2019
DL2: Training and Querying Neural Networks with Logic
Marc Fischer, Mislav Balunović, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, Martin Vechev
ICML
2019
Boosting Robustness Certification of Neural Networks
Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev
ICLR
2019
A Provable Defense for Deep Residual Networks
Matthew Mirman, Gagandeep Singh, Martin Vechev
ArXiv
2019
An Abstract Domain for Certifying Neural Networks
Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev
ACM POPL
2019
2018
Fast and Effective Robustness Certification
Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
NIPS
2018
Differentiable Abstract Interpretation for Provably Robust Neural Networks
Matthew Mirman, Timon Gehr, Martin Vechev
ICML
2018
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Timon Gehr, Matthew Mirman, Dana Drachsler-Cohen, Petar Tsankov, Swarat Chaudhuri, Martin Vechev
IEEE S&P
2018
Talks
Safe and Robust Deep Learning
Waterloo ML + Security + Verification Workshop
Safe and Robust Deep Learning
University of Edinburgh, Robust Artificial Intelligence for Neurorobotics 2019
AI2: AI Safety and Robustness with Abstract Interpretation
Machine Learning meets Formal Methods, FLOC 2018