Marc Fischer

发表

Private and Reliable Neural Network Inference

Martin T. Vechev, Nikola Jovanovic, Samuel Steffen, 2022, CCS.

Efﬁcient Robustness Veriﬁcation of Neural Ordinary Differential Equations

Martin T. Vechev, Mark Niklas Müller, Mustafa Zeqiri, 2022 .

Prompting Is Programming: A Query Language For Large Language Models

Martin T. Vechev, Luca Beurer-Kellner, Marc Fischer, 2022, ArXiv.

DL2: Training and Querying Neural Networks with Logic

Mislav Balunovic, Timon Gehr, Ce Zhang, 2019, ICML.

Efficient Certified Training and Robustness Verification of Neural ODEs

Martin T. Vechev, Mustafa Zeqiri, Marc Fischer, 2023, ICLR.

Robust and Accurate - Compositional Architectures for Randomized Smoothing

Martin T. Vechev, Marc Fischer, Mark Niklas Muller, 2022, ArXiv.

Boosting Randomized Smoothing with Variance Reduced Classifiers pdf

Marc Fischer, Martin T. Vechev, Miklós Z. Horváth, 2021, ICLR.

Scalable Certified Segmentation via Randomized Smoothing

Martin T. Vechev, Maximilian Baader, Marc Fischer, 2021, ICML.

Prompting Is Programming: A Query Language For Large Language Models

Martin T. Vechev, Luca Beurer-Kellner, Marc Fischer, 2022, arXiv.org.

Certified Defense to Image Transformations via Randomized Smoothing

Maximilian Baader, Martin Vechev, Marc Fischer, 2020, NeurIPS.

(De-)Randomized Smoothing for Decision Stump Ensembles

Martin T. Vechev, Marc Fischer, Mark Niklas Muller, 2022, NeurIPS.

VARIANCE REDUCED CLASSIFIERS

Martin T. Vechev, Mark Niklas Müller, Marc Fischer, 2022 .

Certified Training: Small Boxes are All You Need

Martin T. Vechev, Franziska Eckert, Marc Fischer, 2022, ICLR.

Effective Certification of Monotone Deep Equilibrium Models pdf

Martin T. Vechev, Marc Fischer, Mark Niklas Müller, 2021, ArXiv.

Online Robustness Training for Deep Reinforcement Learning

Martin T. Vechev, M. Mirman, Steven Stalder, 2019, ArXiv.

Shared Certificates for Neural Network Verification

Martin T. Vechev, Dimitar I. Dimitrov, C. Sprecher, 2021, CAV.

Learning Certified Individually Fair Representations pdf

Martin Vechev, Marc Fischer, Martin T. Vechev, 2020, NeurIPS.

Prompting Is Programming: A Query Language for Large Language Models

Martin T. Vechev, Luca Beurer-Kellner, Marc Fischer, 2022, Proc. ACM Program. Lang..

TAPS: Connecting Certified and Adversarial Training

Martin T. Vechev, Marc Fischer, Yuhao Mao, 2023, ArXiv.

Understanding Certified Training with Interval Bound Propagation

Martin T. Vechev, Marc Fischer, Yuhao Mao, 2023, ICLR.

Certification of Semantic Perturbations via Randomized Smoothing pdf

Maximilian Baader, Martin Vechev, Marc Fischer, 2020, ArXiv.

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks

Martin T. Vechev, Marc Fischer, Mark Niklas Muller, 2021, Proc. ACM Program. Lang..

Distilled Agent DQN for Provable Adversarial Robustness

Matthew Mirman, Martin Vechev, Martin T. Vechev, 2018 .

Controlled Text Generation via Language Model Arithmetic

Martin T. Vechev, Luca Beurer-Kellner, Marc Fischer, 2023, ArXiv.

Shared Certificates for Neural Network Verification

Martin T. Vechev, Dimitar I. Dimitrov, C. Sprecher, 2021, CAV.

Evading Data Contamination Detection for Language Models is (too) Easy

Martin T. Vechev, Maximilian Baader, Marc Fischer, 2024, ArXiv.

Boosting Randomized Smoothing with Variance Reduced Classifiers

Martin T. Vechev, Mark Niklas Müller, Marc Fischer, 2021, ICLR.

Prompt Sketching for Large Language Models

Martin T. Vechev, Luca Beurer-Kellner, Marc Fischer, 2023, ArXiv.

Certified Defense to Image Transformations via Randomized Smoothing

Martin T. Vechev, Maximilian Baader, Marc Fischer, 2020, NeurIPS.

Overcoming the Paradox of Certified Training with Gaussian Smoothing

Martin T. Vechev, Maximilian Baader, Marc Fischer, 2024, ArXiv.

TAPS: Connecting Certified and Adversarial Training

Martin T. Vechev, Marc Fischer, Yuhao Mao, 2023, NeurIPS.