Martin Vechev

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