Martin Vechev
- Papers
- 27
Cite
Notes
Only stored in your browser.
Authored papers
27Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
arXiv 2026
Watermarking Autoregressive Image Generation
arXiv 2025
Mind the Gap: A Practical Attack on GGUF Quantization
arXiv 2025
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
arXiv 2025
COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
arXiv 2024
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
arXiv 2024
BgGPT 1.0: Extending English-centric LLMs to other languages
arXiv 2024
A Synthetic Dataset for Personal Attribute Inference
arXiv 2024
Discovering Spoofing Attempts on Language Model Watermarks
arXiv 2024
Large Language Models for Code: Security Hardening and Adversarial Testing
arXiv 2023
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
arXiv 2023
Controlled Text Generation via Language Model Arithmetic
arXiv 2023
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
arXiv 2023
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
arXiv 2023
From Principle to Practice: Vertical Data Minimization for Machine Learning
arXiv 2023
Understanding Certified Training with Interval Bound Propagation
arXiv 2023
Private and Reliable Neural Network Inference
arXiv 2022
On Distribution Shift in Learning-based Bug Detectors
arXiv 2022
Certified Training: Small Boxes are All You Need
arXiv 2022
FARE: Provably Fair Representation Learning with Practical Certificates
arXiv 2022
LAMP: Extracting Text from Gradients with Language Model Priors
arXiv 2022
Fair Normalizing Flows
fair-normalizing-flows-1
Robustness Certification for Point Cloud Models
ICCV 2021 10
Latent Space Smoothing for Individually Fair Representations
latent-space-smoothing-for-individually-fair
Efficient Certification of Spatial Robustness
arXiv 2020
Learning Certified Individually Fair Representations
NeurIPS 2020 12
A Provable Defense for Deep Residual Networks
arXiv 2019
Affiliations
Frequent co-authors
10from 27 papers