关注
Martin Vechev
Martin Vechev
Full Professor of Computer Science, ETH Zurich; Scientific Director, INSAIT;
在 inf.ethz.ch 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
J Dekoninck, M Baader, M Vechev
arXiv preprint arXiv:2409.00696, 2024
2024
Practical Attacks against Black-box Code Completion Engines
S Jenko, J He, N Mündler, M Vero, M Vechev
arXiv preprint arXiv:2408.02509, 2024
2024
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging
A Alexandrov, V Raychev, MN Müller, C Zhang, M Vechev, K Toutanova
arXiv preprint arXiv:2407.08699, 2024
12024
Modular Synthesis of Efficient Quantum Uncomputation
H Venev, T Gehr, D Dimitrov, M Vechev
arXiv preprint arXiv:2406.14227, 2024
12024
Code Agents are State of the Art Software Testers
N Mündler, MN Müller, J He, M Vechev
arXiv preprint arXiv:2406.12952, 2024
12024
A Synthetic Dataset for Personal Attribute Inference
H Yukhymenko, R Staab, M Vero, M Vechev
arXiv preprint arXiv:2406.07217, 2024
12024
CTBENCH: A Library and Benchmark for Certified Training
Y Mao, S Balauca, M Vechev
arXiv preprint arXiv:2406.04848, 2024
2024
Exploiting LLM Quantization
K Egashira, M Vero, R Staab, J He, M Vechev
arXiv preprint arXiv:2405.18137, 2024
2024
Back to the Drawing Board for Fair Representation Learning
A Pouget, N Jovanović, M Vero, R Staab, M Vechev
arXiv preprint arXiv:2405.18161, 2024
2024
ConStat: Performance-Based Contamination Detection in Large Language Models
J Dekoninck, MN Müller, M Vechev
arXiv preprint arXiv:2405.16281, 2024
12024
DAGER: Exact Gradient Inversion for Large Language Models
I Petrov, DI Dimitrov, M Baader, MN Müller, M Vechev
arXiv preprint arXiv:2405.15586, 2024
2024
From principle to practice: Vertical data minimization for machine learning
R Staab, N Jovanović, M Balunović, M Vechev
2024 IEEE Symposium on Security and Privacy (SP), 4733-4752, 2024
22024
Black-Box Detection of Language Model Watermarks
T Gloaguen, N Jovanović, R Staab, M Vechev
ICML 2024 Workshop on Foundation Models in the Wild, 2024
2024
Synthetiq: Fast and Versatile Quantum Circuit Synthesis
A Paradis, J Dekoninck, B Bichsel, M Vechev
Proceedings of the ACM on Programming Languages 8 (OOPSLA1), 55-82, 2024
12024
Private Attribute Inference from Images with Vision-Language Models
B Tömekçe, M Vero, R Staab, M Vechev
arXiv preprint arXiv:2404.10618, 2024
12024
Overcoming the Paradox of Certified Training with Gaussian Smoothing
S Balauca, MN Müller, Y Mao, M Baader, M Fischer, M Vechev
arXiv preprint arXiv:2403.07095, 2024
12024
Spear: Exact gradient inversion of batches in federated learning
DI Dimitrov, M Baader, MN Müller, M Vechev
arXiv preprint arXiv:2403.03945, 2024
22024
Watermark stealing in large language models
N Jovanović, R Staab, M Vechev
arXiv preprint arXiv:2402.19361, 2024
122024
Large language models are advanced anonymizers
R Staab, M Vero, M Balunović, M Vechev
arXiv preprint arXiv:2402.13846, 2024
52024
Deepcode AI fix: Fixing security vulnerabilities with large language models
B Berabi, A Gronskiy, V Raychev, G Sivanrupan, V Chibotaru, M Vechev
arXiv preprint arXiv:2402.13291, 2024
42024
系统目前无法执行此操作，请稍后再试。
文章 1–20