ML Anthology

Vechev, Martin

109 publications

ICML 2025 A Unified Approach to Routing and Cascading for LLMs Jasper Dekoninck, Maximilian Baader, Martin Vechev
ICLRW 2025 A Unified Approach to Routing and Cascading for LLMs Jasper Dekoninck, Maximilian Baader, Martin Vechev
ICML 2025 Automated Benchmark Generation for Repository-Level Coding Tasks Konstantinos Vergopoulos, Mark Niklas Mueller, Martin Vechev
ICLRW 2025 Automated Benchmark Generation for Repository-Level Coding Tasks Konstantinos Vergopoulos, Mark Niklas Mueller, Martin Vechev
ICML 2025 Average Certified Radius Is a Poor Metric for Randomized Smoothing Chenhao Sun, Yuhao Mao, Mark Niklas Mueller, Martin Vechev
ICML 2025 BaxBench: Can LLMs Generate Correct and Secure Backends? Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev
ICLRW 2025 BaxBench: Can LLMs Generate Correct and Secure Backends? Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev
ICML 2025 Black-Box Adversarial Attacks on LLM-Based Code Completion Slobodan Jenko, Niels Mündler, Jingxuan He, Mark Vero, Martin Vechev
ICLRW 2025 Black-Box Adversarial Attacks on LLM-Based Code Completion Slobodan Jenko, Niels Mündler, Jingxuan He, Mark Vero, Martin Vechev
ICLR 2025 Black-Box Detection of Language Model Watermarks Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICML 2025 CTBench: A Library and Benchmark for Certified Training Yuhao Mao, Stefan Balauca, Martin Vechev
ICML 2025 Discovering Spoofing Attempts on Language Model Watermarks Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICLRW 2025 Discovering Spoofing Attempts on Language Model Watermarks Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICLR 2025 GRAIN: Exact Graph Reconstruction from Gradients Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar Iliev Dimitrov, Martin Vechev
TMLR 2025 Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations Stefan Balauca, Mark Niklas Mueller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
ICLR 2025 Language Models Are Advanced Anonymizers Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev
NeurIPS 2025 MathArena: Evaluating LLMs on Uncontaminated Math Competitions Mislav Balunovic, Jasper Dekoninck, Ivo Petrov, Nikola Jovanović, Martin Vechev
ICML 2025 MathConstruct: Challenging LLM Reasoning with Constructive Proofs Mislav Balunovic, Jasper Dekoninck, Nikola Jovanović, Ivo Petrov, Martin Vechev
ICLRW 2025 MathConstruct: Challenging LLM Reasoning with Constructive Proofs Jasper Dekoninck, Mislav Balunovic, Nikola Jovanović, Ivo Petrov, Martin Vechev
ICML 2025 Mind the Gap: A Practical Attack on GGUF Quantization Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev
ICLRW 2025 Mind the Gap: A Practical Attack on GGUF Quantization Kazuki Egashira, Robin Staab, Mark Vero, Jingxuan He, Martin Vechev
NeurIPS 2025 MixAT: Combining Continuous and Discrete Adversarial Training for LLMs Csaba Dékány, Stefan Balauca, Dimitar Iliev Dimitrov, Robin Staab, Martin Vechev
ICLR 2025 Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation Jasper Dekoninck, Maximilian Baader, Martin Vechev
ICLRW 2025 Towards Watermarking of Open-Source LLMs Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICLRW 2025 Type-Constrained Code Generation with Language Models Niels Mündler, Jingxuan He, Hao Wang, Koushik Sen, Dawn Song, Martin Vechev
ICLR 2025 Ward: Provable RAG Dataset Inference via LLM Watermarks Nikola Jovanović, Robin Staab, Maximilian Baader, Martin Vechev
NeurIPS 2025 Watermarking Autoregressive Image Generation Nikola Jovanović, Ismail Labiad, Tomas Soucek, Martin Vechev, Pierre Fernandez
NeurIPS 2024 A Synthetic Dataset for Personal Attribute Inference Hanna Yukhymenko, Robin Staab, Mark Vero, Martin Vechev
ICMLW 2024 AI Agents with Formal Security Guarantees Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, Martin Vechev
ICLR 2024 Beyond Memorization: Violating Privacy via Inference with Large Language Models Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev
ICMLW 2024 Black-Box Detection of Language Model Watermarks Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICMLW 2024 Black-Box Detection of Language Model Watermarks Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
ICMLW 2024 Code Agents Are State of the Art Software Testers Niels Mündler, Mark Niklas Mueller, Jingxuan He, Martin Vechev
ICMLW 2024 Code Agents Are State of the Art Software Testers Niels Mündler, Mark Niklas Mueller, Jingxuan He, Martin Vechev
NeurIPS 2024 ConStat: Performance-Based Contamination Detection in Large Language Models Jasper Dekoninck, Mark Niklas Müller, Martin Vechev
NeurIPSW 2024 Constraint-Based Synthetic Data Generation for LLM Mathematical Reasoning Timofey Fedoseev, Dimitar Iliev Dimitrov, Timon Gehr, Martin Vechev
ICLR 2024 Controlled Text Generation via Language Model Arithmetic Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev
ICML 2024 CuTS: Customizable Tabular Synthetic Data Generation Mark Vero, Mislav Balunovic, 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 Exploiting LLM Quantization Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev
ICMLW 2024 Exploiting LLM Quantization Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev
ICLR 2024 Expressivity of ReLU-Networks Under Convex Relaxations Maximilian Baader, Mark Niklas Mueller, Yuhao Mao, Martin Vechev
ICML 2024 Guiding LLMs the Right Way: Fast, Non-Invasive Constrained Generation Luca Beurer-Kellner, Marc Fischer, Martin Vechev
ICLR 2024 Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning Kostadin Garov, Dimitar Iliev Dimitrov, Nikola Jovanović, Martin Vechev
ICML 2024 Instruction Tuning for Secure Code Generation Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin Vechev
ICLRW 2024 Instruction Tuning for Secure Code Generation Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin Vechev
ICLRW 2024 Large Language Models Are Anonymizers Robin Staab, Mark Vero, Mislav Balunovic, Martin Vechev
NeurIPS 2024 Private Attribute Inference from Images with Vision-Language Models Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev
ICMLW 2024 Private Attribute Inference from Images with Vision-Language Models Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev
ICML 2024 Prompt Sketching for Large Language Models Luca Beurer-Kellner, Mark Niklas Mueller, Marc Fischer, 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
ICLR 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 Mueller, Marc Fischer, Martin Vechev
ICML 2024 Watermark Stealing in Large Language Models Nikola Jovanović, Robin Staab, Martin Vechev
ICLRW 2024 Watermark Stealing in Large Language Models Nikola Jovanović, Robin Staab, Martin Vechev
NeurIPS 2023 Automated Classification of Model Errors on ImageNet Momchil Peychev, Mark Müller, Marc Fischer, Martin Vechev
ICLR 2023 Certified Training: Small Boxes Are All You Need Mark Niklas Mueller, Franziska Eckert, Marc Fischer, Martin Vechev
NeurIPS 2023 Connecting Certified and Adversarial Training Yuhao Mao, Mark Müller, Marc Fischer, Martin Vechev
ICLR 2023 Efficient Certified Training and Robustness Verification of Neural ODEs Mustafa Zeqiri, Mark Niklas Mueller, Marc Fischer, Martin Vechev
ICML 2023 FARE: Provably Fair Representation Learning with Practical Certificates Nikola Jovanović, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin Vechev
ICMLW 2023 Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning Kostadin Garov, Dimitar Iliev Dimitrov, Nikola Jovanović, Martin Vechev
ICLR 2023 Human-Guided Fair Classification for Natural Language Processing Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin Vechev
ICMLW 2023 Incentivizing Honesty Among Competitors in Collaborative Learning Florian E. Dorner, Nikola Konstantinov, Georgi Stoyanov Pashaliev, Martin Vechev
NeurIPS 2023 Incentivizing Honesty Among Competitors in Collaborative Learning and Optimization Florian E. Dorner, Nikola Konstantinov, Georgi Pashaliev, Martin Vechev
ICMLW 2023 Large Language Models for Code: Security Hardening and Adversarial Testing Jingxuan He, Martin Vechev
ICML 2023 TabLeak: Tabular Data Leakage in Federated Learning Mark Vero, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin Vechev
NeurIPS 2022 (De-)Randomized Smoothing for Decision Stump Ensembles Miklós Horváth, Mark Müller, Marc Fischer, Martin Vechev
ICLR 2022 Bayesian Framework for Gradient Leakage Mislav Balunovic, Dimitar Iliev Dimitrov, Robin Staab, Martin Vechev
ICLR 2022 Boosting Randomized Smoothing with Variance Reduced Classifiers Miklós Z. Horváth, Mark Niklas Mueller, Marc Fischer, Martin Vechev
NeurIPSW 2022 Certified Training: Small Boxes Are All You Need Mark Niklas Mueller, Franziska Eckert, Marc Fischer, Martin Vechev
ICLR 2022 Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound Claudio Ferrari, Mark Niklas Mueller, Nikola Jovanović, Martin Vechev
TMLR 2022 Data Leakage in Federated Averaging Dimitar Iliev Dimitrov, Mislav Balunovic, Nikola Konstantinov, Martin Vechev
NeurIPSW 2022 Efficient Robustness Verification of Neural Ordinary Differential Equations Mustafa Zeqiri, Mark Niklas Mueller, Marc Fischer, Martin Vechev
NeurIPSW 2022 FARE: Provably Fair Representation Learning Nikola Jovanović, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin Vechev
ICLR 2022 Fair Normalizing Flows Mislav Balunovic, Anian Ruoss, Martin Vechev
NeurIPSW 2022 Generating Intuitive Fairness Specifications for Natural Language Processing Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin Vechev
NeurIPSW 2022 Just Avoid Robust Inaccuracy: Boosting Robustness Without Sacrificing Accuracy Yannick Merkli, Pavol Bielik, Petar Tsankov, Martin Vechev
NeurIPS 2022 LAMP: Extracting Text from Gradients with Language Model Priors Mislav Balunovic, Dimitar Dimitrov, Nikola Jovanović, Martin Vechev
ECCV 2022 Latent Space Smoothing for Individually Fair Representations Momchil Peychev, Anian Ruoss, Mislav Balunović, Maximilian Baader, Martin Vechev
NeurIPS 2022 Learning to Configure Computer Networks with Neural Algorithmic Reasoning Luca Beurer-Kellner, Martin Vechev, Laurent Vanbever, Petar Veličković
ICML 2022 On Distribution Shift in Learning-Based Bug Detectors Jingxuan He, Luca Beurer-Kellner, Martin Vechev
TMLR 2022 On the Paradox of Certified Training Nikola Jovanović, Mislav Balunovic, Maximilian Baader, Martin Vechev
ICLR 2022 Provably Robust Adversarial Examples Dimitar Iliev Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev
TMLR 2022 The Fundamental Limits of Neural Networks for Interval Certified Robustness Matthew B Mirman, Maximilian Baader, Martin Vechev
NeurIPS 2021 Automated Discovery of Adaptive Attacks on Adversarial Defenses Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev
ICMLW 2021 Automated Discovery of Adaptive Attacks on Adversarial Defenses Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev
ICLR 2021 Certify or Predict: Boosting Certified Robustness with Compositional Architectures Mark Niklas Mueller, Mislav Balunovic, Martin Vechev
ICML 2021 PODS: Policy Optimization via Differentiable Simulation Miguel Angel Zamora Mora, Momchil Peychev, Sehoon Ha, Martin Vechev, Stelian Coros
ICCV 2021 Robustness Certification for Point Cloud Models Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev
ICML 2021 Scalable Certified Segmentation via Randomized Smoothing Marc Fischer, Maximilian Baader, Martin Vechev
ICML 2021 TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer Berkay Berabi, Jingxuan He, Veselin Raychev, Martin Vechev
ICML 2020 Adversarial Attacks on Probabilistic Autoregressive Forecasting Models Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin Vechev
ICML 2020 Adversarial Robustness for Code Pavol Bielik, Martin Vechev
ICLR 2020 Adversarial Training and Provable Defenses: Bridging the Gap Mislav Balunovic, Martin Vechev
NeurIPS 2020 Certified Defense to Image Transformations via Randomized Smoothing Marc Fischer, Maximilian Baader, Martin Vechev
ICLR 2020 Guiding Program Synthesis by Learning to Generate Examples Larissa Laich, Pavol Bielik, Martin Vechev
NeurIPS 2020 Learning Certified Individually Fair Representations Anian Ruoss, Mislav Balunovic, Marc Fischer, Martin Vechev
ICLR 2020 Universal Approximation with Certified Networks Maximilian Baader, Matthew Mirman, Martin Vechev
NeurIPS 2019 Beyond the Single Neuron Convex Barrier for Neural Network Certification Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin Vechev
ICLR 2019 Boosting Robustness Certification of Neural Networks Gagandeep Singh, Timon Gehr, Markus Püschel, Martin Vechev
NeurIPS 2019 Certifying Geometric Robustness of Neural Networks Mislav Balunovic, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev
ICML 2019 DL2: Training and Querying Neural Networks with Logic Marc Fischer, Mislav Balunovic, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, Martin Vechev
ICML 2018 Differentiable Abstract Interpretation for Provably Robust Neural Networks Matthew Mirman, Timon Gehr, Martin Vechev
NeurIPS 2018 Fast and Effective Robustness Certification Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
NeurIPS 2018 Learning to Solve SMT Formulas Mislav Balunovic, Pavol Bielik, Martin Vechev
ICML 2018 Training Neural Machines with Trace-Based Supervision Matthew Mirman, Dimitar Dimitrov, Pavle Djordjevic, Timon Gehr, Martin Vechev
COLT 2017 Learning Disjunctions of Predicates Nader H. Bshouty, Dana Drachsler-Cohen, Martin Vechev, Eran Yahav
ICML 2016 PHOG: Probabilistic Model for Code Pavol Bielik, Veselin Raychev, Martin Vechev