Search Results for author: Tom Wollschläger

Found 5 papers, 2 papers with code

Attacking Large Language Models with Projected Gradient Descent

no code implementations14 Feb 2024 Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Johannes Gasteiger, Stephan Günnemann

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts.

Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness

1 code implementation16 Aug 2023 Francesco Campi, Lukas Gosch, Tom Wollschläger, Yan Scholten, Stephan Günnemann

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs).

Adversarial Robustness Subgraph Counting

Uncertainty Estimation for Molecules: Desiderata and Methods

no code implementations20 Jun 2023 Tom Wollschläger, Nicholas Gao, Bertrand Charpentier, Mohamed Amine Ketata, Stephan Günnemann

Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories.

Efficient MILP Decomposition in Quantum Computing for ReLU Network Robustness

1 code implementation30 Apr 2023 Nicola Franco, Tom Wollschläger, Benedikt Poggel, Stephan Günnemann, Jeanette Miriam Lorenz

We conduct a detailed analysis for the decomposition of MILP with Benders and Dantzig-Wolfe methods.

Localized Randomized Smoothing for Collective Robustness Certification

no code implementations28 Oct 2022 Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, Stephan Günnemann

We further show that this approach is beneficial for the larger class of softly local models, where each output is dependent on the entire input but assigns different levels of importance to different input regions (e. g. based on their proximity in the image).

Image Segmentation Node Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.