← Authors

Martin Vechev

79 papers · 2016–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (9) 🌈 Renaissance Researcher (11) 🌍 Conference Polyglot (9) 🐝 Cross-Pollinator (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏠 Conference Loyalist (20) 🀝 Dynamic Duo (18) πŸ‘‘ Triple Crown πŸ† Grand Slam 🧬 Topic Evolution πŸ† Keyword Champion (3) ⚑ Prolific Year (19) ❓ The Questioner πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (194) πŸ’Ž Century Club (79) πŸ”₯ Unstoppable (10)

Conferences

ICML (26) ICLR (24) NIPS (20) NSDI (4) AAAI (1) COLT (1) ECCV (1) EMNLP (1) ICCV (1)

Top co-authors

Mislav Balunovic (18) Maximilian Baader (14) Marc Fischer (14) Mark Vero (11) Robin Staab (11) Nikola Jovanović (10) Mark Niklas Mueller (10) Jingxuan He (9) Timon Gehr (7) Gagandeep Singh (7)

Research topics

Privacy (3)

Keywords

adversarial robustness (6) federated learning (5) adversarial attack (5) formal verification (5) large language model (4) robustness certification (3) code generation (3) randomized smoothing (3) privacy attack (3) computer vision (3) neural network (3) certified robustness (2) adversarial perturbation (2) adversarial defense (2) language model (2) neural network verification (2) benchmark evaluation (2) convex relaxation (2) transfer learning (2) program synthesis (2)

Papers

BaxBench: Can LLMs Generate Correct and Secure Backends? ICML 2025
Automated Benchmark Generation for Repository-Level Coding Tasks ICML 2025
Average Certified Radius is a Poor Metric for Randomized Smoothing ICML 2025
Discovering Spoofing Attempts on Language Model Watermarks ICML 2025
CTBench: A Library and Benchmark for Certified Training ICML 2025
Black-Box Adversarial Attacks on LLM-Based Code Completion ICML 2025
Mind the Gap: A Practical Attack on GGUF Quantization ICML 2025
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation ICLR 2025
GRAIN: Exact Graph Reconstruction from Gradients ICLR 2025
Language Models are Advanced Anonymizers ICLR 2025
Ward: Provable RAG Dataset Inference via LLM Watermarks ICLR 2025
Black-Box Detection of Language Model Watermarks ICLR 2025
A Unified Approach to Routing and Cascading for LLMs ICML 2025
MathConstruct: Challenging LLM Reasoning with Constructive Proofs ICML 2025
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging EMNLP 2024
Prompt Sketching for Large Language Models ICML 2024
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation ICML 2024
Expressivity of ReLU-Networks under Convex Relaxations ICLR 2024
Understanding Certified Training with Interval Bound Propagation ICLR 2024
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning ICLR 2024
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation ICLR 2024
Beyond Memorization: Violating Privacy via Inference with Large Language Models ICLR 2024
Controlled Text Generation via Language Model Arithmetic ICLR 2024
Exploiting LLM Quantization NIPS 2024
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents NIPS 2024
DAGER: Exact Gradient Inversion for Large Language Models NIPS 2024
ConStat: Performance-Based Contamination Detection in Large Language Models NIPS 2024
Private Attribute Inference from Images with Vision-Language Models NIPS 2024
SPEAR: Exact Gradient Inversion of Batches in Federated Learning NIPS 2024
A Synthetic Dataset for Personal Attribute Inference NIPS 2024
CuTS: Customizable Tabular Synthetic Data Generation ICML 2024
Watermark Stealing in Large Language Models ICML 2024
Instruction Tuning for Secure Code Generation ICML 2024
TabLeak: Tabular Data Leakage in Federated Learning ICML 2023
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization NIPS 2023
Automated Classification of Model Errors on ImageNet NIPS 2023
Connecting Certified and Adversarial Training NIPS 2023
Efficient Certified Training and Robustness Verification of Neural ODEs ICLR 2023
Human-Guided Fair Classification for Natural Language Processing ICLR 2023
Certified Training: Small Boxes are All You Need ICLR 2023
FARE: Provably Fair Representation Learning with Practical Certificates ICML 2023
Fair Normalizing Flows ICLR 2022
Provably Robust Adversarial Examples ICLR 2022
Bayesian Framework for Gradient Leakage ICLR 2022
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound ICLR 2022
On Distribution Shift in Learning-based Bug Detectors ICML 2022
Latent Space Smoothing for Individually Fair Representations ECCV 2022
LAMP: Extracting Text from Gradients with Language Model Priors NIPS 2022
(De-)Randomized Smoothing for Decision Stump Ensembles NIPS 2022
Learning to Configure Computer Networks with Neural Algorithmic Reasoning NIPS 2022
Boosting Randomized Smoothing with Variance Reduced Classifiers ICLR 2022
Metha: Network Verifiers Need To Be Correct Too! NSDI 2021
Efficient Certification of Spatial Robustness AAAI 2021
Robustness Certification for Point Cloud Models ICCV 2021
Automated Discovery of Adaptive Attacks on Adversarial Defenses NIPS 2021
Certify or Predict: Boosting Certified Robustness with Compositional Architectures ICLR 2021
Scalable Certified Segmentation via Randomized Smoothing ICML 2021
PODS: Policy Optimization via Differentiable Simulation ICML 2021
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer ICML 2021
Learning Certified Individually Fair Representations NIPS 2020
Guiding Program Synthesis by Learning to Generate Examples ICLR 2020
Universal Approximation with Certified Networks ICLR 2020
Adversarial Training and Provable Defenses: Bridging the Gap ICLR 2020
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models ICML 2020
Config2Spec: Mining Network Specifications from Network Configurations NSDI 2020
Certified Defense to Image Transformations via Randomized Smoothing NIPS 2020
Adversarial Robustness for Code ICML 2020
Boosting Robustness Certification of Neural Networks ICLR 2019
Certifying Geometric Robustness of Neural Networks NIPS 2019
Beyond the Single Neuron Convex Barrier for Neural Network Certification NIPS 2019
DL2: Training and Querying Neural Networks with Logic ICML 2019
Training Neural Machines with Trace-Based Supervision ICML 2018
Learning to Solve SMT Formulas NIPS 2018
Fast and Effective Robustness Certification NIPS 2018
NetComplete: Practical Network-Wide Configuration Synthesis with Autocompletion NSDI 2018
Net2Text: Query-Guided Summarization of Network Forwarding Behaviors NSDI 2018
Differentiable Abstract Interpretation for Provably Robust Neural Networks ICML 2018
Learning Disjunctions of Predicates COLT 2017
PHOG: Probabilistic Model for Code ICML 2016