no code implementations • 11 Mar 2024 • Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
Training neural networks with high certified accuracy against adversarial examples remains an open problem despite significant efforts.
no code implementations • 7 Feb 2024 • Luca Beurer-Kellner, Marc Fischer, Martin Vechev
To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation.
1 code implementation • 5 Feb 2024 • Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev
Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another.
1 code implementation • 24 Nov 2023 • Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev
In addition, the framework allows for more precise control of generated text than direct prompting and prior controlled text generation (CTG) techniques.
1 code implementation • NeurIPS 2023 • Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
To address this, new label-sets and evaluation protocols have been proposed for ImageNet showing that state-of-the-art models already achieve over 95% accuracy and shifting the focus on investigating why the remaining errors persist.
no code implementations • 8 Nov 2023 • Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin Vechev
This way, sketching grants users more control over the generation process, e. g., by providing a reasoning framework via intermediate instructions, leading to better overall results.
1 code implementation • 17 Jun 2023 • Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
We, then, derive sufficient and necessary conditions on weight matrices for IBP bounds to become exact and demonstrate that these impose strong regularization, explaining the empirically observed trade-off between robustness and accuracy in certified training.
2 code implementations • 8 May 2023 • Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
Training certifiably robust neural networks remains a notoriously hard problem.
1 code implementation • 9 Mar 2023 • Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference.
no code implementations • 12 Dec 2022 • Luca Beurer-Kellner, Marc Fischer, Martin Vechev
We show that LMQL can capture a wide range of state-of-the-art prompting methods in an intuitive way, especially facilitating interactive flows that are challenging to implement with existing high-level APIs.
2 code implementations • 16 Nov 2022 • Marc Fischer, Alexander Bartler, Bin Yang
As such, fine-tuning a model to a downstream task in a parameter-efficient but effective way, e. g. for a new set of classes in the case of semantic segmentation, is of increasing importance.
1 code implementation • 27 Oct 2022 • Nikola Jovanović, Marc Fischer, Samuel Steffen, Martin Vechev
We employ these building blocks to enable privacy-preserving NN inference with robustness and fairness guarantees in a system called Phoenix.
1 code implementation • 10 Oct 2022 • Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin Vechev
To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used.
1 code implementation • 27 May 2022 • Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin Vechev
Whereas most prior work on randomized smoothing focuses on evaluating arbitrary base models approximately under input randomization, the key insight of our work is that decision stump ensembles enable exact yet efficient evaluation via dynamic programming.
1 code implementation • 1 Apr 2022 • Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin Vechev
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks.
1 code implementation • 14 Oct 2021 • Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators.
1 code implementation • 1 Sep 2021 • Marc Fischer, Christian Sprecher, Dimitar I. Dimitrov, Gagandeep Singh, Martin Vechev
We perform an extensive experimental evaluation to demonstrate the effectiveness of shared certificates in reducing the verification cost on a range of datasets and attack specifications on image classifiers including the popular patch and geometric perturbations.
1 code implementation • 1 Jul 2021 • Marc Fischer, Maximilian Baader, Martin Vechev
We present a new certification method for image and point cloud segmentation based on randomized smoothing.
1 code implementation • ICLR 2022 • Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin Vechev
Randomized Smoothing (RS) is a promising method for obtaining robustness certificates by evaluating a base model under noise.
1 code implementation • 5 Aug 2020 • Thomas Küstner, Tobias Hepp, Marc Fischer, Martin Schwartz, Andreas Fritsche, Hans-Ulrich Häring, Konstantin Nikolaou, Fabian Bamberg, Bin Yang, Fritz Schick, Sergios Gatidis, Jürgen Machann
Methods: Quantification and localization of different adipose tissue compartments from whole-body MR images is of high interest to examine metabolic conditions.
1 code implementation • NeurIPS 2020 • Marc Fischer, Maximilian Baader, Martin Vechev
We extend randomized smoothing to cover parameterized transformations (e. g., rotations, translations) and certify robustness in the parameter space (e. g., rotation angle).
1 code implementation • NeurIPS 2020 • Anian Ruoss, Mislav Balunović, Marc Fischer, Martin Vechev
That is, our method enables the data producer to learn and certify a representation where for a data point all similar individuals are at $\ell_\infty$-distance at most $\epsilon$, thus allowing data consumers to certify individual fairness by proving $\epsilon$-robustness of their classifier.
no code implementations • 29 Dec 2019 • Maciej Besta, Marc Fischer, Vasiliki Kalavri, Michael Kapralov, Torsten Hoefler
We also crystallize the meaning of different concepts associated with streaming graph processing, such as dynamic, temporal, online, and time-evolving graphs, edge-centric processing, models for the maintenance of updates, and graph databases.
Distributed, Parallel, and Cluster Computing Databases Data Structures and Algorithms Performance
no code implementations • 3 Nov 2019 • Marc Fischer, Matthew Mirman, Steven Stalder, Martin Vechev
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training.
no code implementations • 25 Sep 2019 • Marc Fischer, Maximilian Baader, Martin Vechev
We present a novel statistical certification method that generalizes prior work based on smoothing to handle richer perturbations.
no code implementations • ICLR 2019 • Marc Fischer, Mislav Balunovic, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, Martin Vechev
We present DL2, a system for training and querying neural networks with logical constraints.
no code implementations • 27 Sep 2018 • Matthew Mirman, Marc Fischer, Martin Vechev
As deep neural networks have become the state of the art for solving complex reinforcement learning tasks, susceptibility to perceptual adversarial examples have become a concern.
no code implementations • 17 Jun 2018 • Karim Armanious, Chenming Jiang, Marc Fischer, Thomas Küstner, Konstantin Nikolaou, Sergios Gatidis, Bin Yang
Image-to-image translation is considered a new frontier in the field of medical image analysis, with numerous potential applications.