Martin T. Vechev

ORCID

Publication Activity (10 Years)

Years Active: 2003-2024
Publications (10 Years): 197

Top Venues

University of Cambridge, UK (PHD)

Education History

University of Cambridge, UK

PHD

Publications

Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
DAGER: Exact Gradient Inversion for Large Language Models. CoRR (2024)
Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
Beyond Memorization: Violating Privacy via Inference with Large Language Models. ICLR (2024)
Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin T. Vechev
Controlled Text Generation via Language Model Arithmetic. ICLR (2024)
Batuhan Tömekçe, Mark Vero, Robin Staab, Martin T. Vechev
Private Attribute Inference from Images with Vision-Language Models. CoRR (2024)
Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin T. Vechev
Instruction Tuning for Secure Code Generation. CoRR (2024)
Jasper Dekoninck, Mark Niklas Müller, Martin T. Vechev
ConStat: Performance-Based Contamination Detection in Large Language Models. CoRR (2024)
Angéline Pouget, Nikola Jovanovic, Mark Vero, Robin Staab, Martin T. Vechev
Back to the Drawing Board for Fair Representation Learning. CoRR (2024)
Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev
Black-Box Detection of Language Model Watermarks. CoRR (2024)
Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin T. Vechev
Exploiting LLM Quantization. CoRR (2024)
Anouk Paradis, Benjamin Bichsel, Martin T. Vechev
Reqomp: Space-constrained Uncomputation for Quantum Circuits. Quantum 8 (2024)
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Automated Classification of Model Errors on ImageNet. CoRR (2024)
Nikola Jovanovic, Robin Staab, Martin T. Vechev
Watermark Stealing in Large Language Models. 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)
Anouk Paradis, Jasper Dekoninck, Benjamin Bichsel, Martin T. Vechev
Synthetiq: Fast and Versatile Quantum Circuit Synthesis. Proc. ACM Program. Lang. 8 (OOPSLA1) (2024)
Niels Mündler, Jingxuan He, Slobodan Jenko, Martin T. Vechev
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation. ICLR (2024)
Luca Beurer-Kellner, Marc Fischer, Martin T. Vechev
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation. CoRR (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)
Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
Large Language Models are Advanced Anonymizers. CoRR (2024)
Berkay Berabi, Alexey Gronskiy, Veselin Raychev, Gishor Sivanrupan, Victor Chibotaru, Martin T. Vechev
DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models. CoRR (2024)
Yuhao Mao, Stefan Balauca, Martin T. Vechev
CTBENCH: A Library and Benchmark for Certified Training. CoRR (2024)
Hanna Yukhymenko, Robin Staab, Mark Vero, Martin T. Vechev
A Synthetic Dataset for Personal Attribute Inference. CoRR (2024)
Hristo Venev, Timon Gehr, Dimitar Dimitrov, Martin T. Vechev
Modular Synthesis of Efficient Quantum Uncomputation. CoRR (2024)
Kostadin Garov, Dimitar Iliev Dimitrov, Nikola Jovanovic, Martin T. Vechev
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning. ICLR (2024)
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev
Code Agents are State of the Art Software Testers. CoRR (2024)
Florian E. Dorner, Nikola Konstantinov, Georgi Pashaliev, Martin T. Vechev
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization. NeurIPS (2023)
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
Certified Training: Small Boxes are All You Need. ICLR (2023)
Mark Vero, Mislav Balunovic, Martin T. Vechev
Programmable Synthetic Tabular Data Generation. CoRR (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)
Robin Staab, Nikola Jovanovic, Mislav Balunovic, Martin T. Vechev
From Principle to Practice: Vertical Data Minimization for Machine Learning. CoRR (2023)
Robin Staab, Mark Vero, Mislav Balunovic, Martin T. Vechev
Beyond Memorization: Violating Privacy Via Inference with 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)
Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin T. Vechev
Human-Guided Fair Classification for Natural Language Processing. ICLR (2023)
Mark Vero, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin T. Vechev
TabLeak: Tabular Data Leakage in Federated Learning. ICML (2023)
Benjamin Bichsel, Anouk Paradis, Maximilian Baader, Martin T. Vechev
Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation. Quantum 7 (2023)
Benjamin Bichsel, Maximilian Baader, Anouk Paradis, Martin T. Vechev
Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation. CoRR (2023)
Niels Mündler, Jingxuan He, Slobodan Jenko, Martin T. Vechev
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation. CoRR (2023)
Florian E. Dorner, Nikola Konstantinov, Georgi Pashaliev, Martin T. Vechev
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization. CoRR (2023)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Understanding Certified Training with Interval Bound Propagation. CoRR (2023)
Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin T. Vechev
Controlled Text Generation via Language Model Arithmetic. CoRR (2023)
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanovic, Martin T. Vechev
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning. CoRR (2023)
Jingxuan He, Martin T. Vechev
Controlling Large Language Models to Generate Secure and Vulnerable Code. CoRR (2023)
Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev
Expressivity of ReLU-Networks under Convex Relaxations. CoRR (2023)
Johan Lokna, Anouk Paradis, Dimitar I. Dimitrov, Martin T. Vechev
Group and Attack: Auditing Differential Privacy. CCS (2023)
Nikola Jovanovic, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin T. Vechev
FARE: Provably Fair Representation Learning with Practical Certificates. ICML (2023)
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
TAPS: Connecting Certified and Adversarial Training. CoRR (2023)
Luca Beurer-Kellner, Marc Fischer, Martin T. Vechev
Prompting Is Programming: A Query Language for Large Language Models. Proc. ACM Program. Lang. 7 (PLDI) (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)
Jingxuan He, Martin T. Vechev
Large Language Models for Code: Security Hardening and Adversarial Testing. CCS (2023)
Mislav Balunovic, Dimitar I. Dimitrov, Nikola Jovanovic, Martin T. Vechev
LAMP: Extracting Text from Gradients with Language Model Priors. NeurIPS (2022)
Jingxuan He, Luca Beurer-Kellner, Martin T. Vechev
On Distribution Shift in Learning-based Bug Detectors. CoRR (2022)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
(De-)Randomized Smoothing for Decision Stump Ensembles. CoRR (2022)
Luca Beurer-Kellner, Martin T. Vechev, Laurent Vanbever, Petar Velickovic
Learning to Configure Computer Networks with Neural Algorithmic Reasoning. CoRR (2022)
Mislav Balunovic, Dimitar Iliev Dimitrov, Robin Staab, Martin T. Vechev
Bayesian Framework for Gradient Leakage. ICLR (2022)
Dimitar Iliev Dimitrov, Mislav Balunovic, Nikola Konstantinov, Martin T. Vechev
Data Leakage in Federated Averaging. Trans. Mach. Learn. Res. 2022 (2022)
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
Boosting Randomized Smoothing with Variance Reduced Classifiers. ICLR (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)
Samuel Steffen, Benjamin Bichsel, Martin T. Vechev
Zapper: Smart Contracts with Data and Identity Privacy. CCS (2022)
Marc Fischer, Christian Sprecher, Dimitar I. Dimitrov, Gagandeep Singh, Martin T. Vechev
Shared Certificates for Neural Network Verification. CAV (1) (2022)
Dimitar Iliev Dimitrov, Gagandeep Singh, Timon Gehr, Martin T. Vechev
Provably Robust Adversarial Examples. ICLR (2022)
Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin T. Vechev
Human-Guided Fair Classification for Natural Language Processing. CoRR (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)
Mark Vero, Mislav Balunovic, Dimitar I. Dimitrov, Martin T. Vechev
Data Leakage in Tabular Federated Learning. CoRR (2022)
Luca Beurer-Kellner, Martin T. Vechev, Laurent Vanbever, Petar Velickovic
Learning to Configure Computer Networks with Neural Algorithmic Reasoning. NeurIPS (2022)
Nikola Jovanovic, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
On the Paradox of Certified Training. Trans. Mach. Learn. Res. 2022 (2022)
Momchil Peychev, Anian Ruoss, Mislav Balunovic, Maximilian Baader, Martin T. Vechev
Latent Space Smoothing for Individually Fair Representations. ECCV (13) (2022)
Dimitar I. Dimitrov, Mislav Balunovic, Nikola Konstantinov, Martin T. Vechev
Data Leakage in Federated Averaging. CoRR (2022)
Nikola Jovanovic, Marc Fischer, Samuel Steffen, Martin T. Vechev
Private and Reliable Neural Network Inference. CoRR (2022)
Dimitar I. Dimitrov, Mislav Balunovic, Nikola Jovanovic, Martin T. Vechev
LAMP: Extracting Text from Gradients with Language Model Priors. CoRR (2022)
Mislav Balunovic, Anian Ruoss, Martin T. Vechev
Fair Normalizing Flows. ICLR (2022)
Pesho Ivanov, Benjamin Bichsel, Martin T. Vechev
Fast and Optimal Sequence-to-Graph Alignment Guided by Seeds. RECOMB (2022)
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound. ICLR (2022)
Nikola Jovanovic, Marc Fischer, Samuel Steffen, Martin T. Vechev
Private and Reliable Neural Network Inference. CCS (2022)
Jingxuan He, Luca Beurer-Kellner, Martin T. Vechev
On Distribution Shift in Learning-based Bug Detectors. ICML (2022)
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
Certified Training: Small Boxes are All You Need. CoRR (2022)
Nikola Jovanovic, Mislav Balunovic, Dimitar I. Dimitrov, Martin T. Vechev
FARE: Provably Fair Representation Learning. CoRR (2022)
Matthew Mirman, Maximilian Baader, Martin T. Vechev
The Fundamental Limits of Neural Networks for Interval Certified Robustness. Trans. Mach. Learn. Res. 2022 (2022)
Samuel Steffen, Benjamin Bichsel, Roger Baumgartner, Martin T. Vechev
ZeeStar: Private Smart Contracts by Homomorphic Encryption and Zero-knowledge Proofs. IEEE Symposium on Security and Privacy (2022)
Berkay Berabi, Jingxuan He, Veselin Raychev, Martin T. Vechev
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer. ICML (2021)
Gregory Bonaert, Dimitar I. Dimitrov, Maximilian Baader, Martin T. Vechev
Fast and precise certification of transformers. PLDI (2021)
Christian Sprecher, Marc Fischer, Dimitar I. Dimitrov, Gagandeep Singh, Martin T. Vechev
Shared Certificates for Neural Network Verification. CoRR (2021)
Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
Robustness Certification for Point Cloud Models. CoRR (2021)
Mislav Balunovic, Dimitar I. Dimitrov, Robin Staab, Martin T. Vechev
Bayesian Framework for Gradient Leakage. CoRR (2021)
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
Precise Multi-Neuron Abstractions for Neural Network Certification. CoRR (2021)
Jingxuan He, Cheng-Chun Lee, Veselin Raychev, Martin T. Vechev
Learning to find naming issues with big code and small supervision. PLDI (2021)
Mark Niklas Müller, Mislav Balunovic, Martin T. Vechev
Certify or Predict: Boosting Certified Robustness with Compositional Architectures. ICLR (2021)
Matthew Mirman, Alexander Hägele, Pavol Bielik, Timon Gehr, Martin T. Vechev
Robustness certification with generative models. PLDI (2021)
Rüdiger Birkner, Tobias Brodmann, Petar Tsankov, Laurent Vanbever, Martin T. Vechev
Metha: Network Verifiers Need To Be Correct Too! NSDI (2021)
Anian Ruoss, Maximilian Baader, Mislav Balunovic, Martin T. Vechev
Efficient Certification of Spatial Robustness. AAAI (2021)
Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
Robustness Certification for Point Cloud Models. ICCV (2021)
Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin T. Vechev
Automated Discovery of Adaptive Attacks on Adversarial Defenses. NeurIPS (2021)
Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin T. Vechev
Automated Discovery of Adaptive Attacks on Adversarial Defenses. CoRR (2021)
Jingxuan He, Gishor Sivanrupan, Petar Tsankov, Martin T. Vechev
Learning to Explore Paths for Symbolic Execution. CCS (2021)

Martin T. Vechev.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Martin T. Vechev