AIConfPaper
← Search

Johannes Gasteiger

13 accepted papers

2025

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Vincent Cohen-Addad, Johannes Gasteiger, Stephan Günnemann
ICML 2025poster

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a manually designed start of a harmful answer to an inappropriate…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

Tom Wollschläger, Jannes Elstner, Simon Geisler, Vincent Cohen-Addad, Stephan Günnemann, Johannes Gasteiger
ICML 2025poster

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a *single* refusal direction in the model's activation space determines w…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Accelerating Molecular Graph Neural Networks via Knowledge Distillation

Filip Ekström Kelvinius, Dimitar Georgiev, Artur Toshev, Johannes Gasteiger
NeurIPS 2023poster

Recent advances in graph neural networks (GNNs) have enabled more comprehensive modeling of molecules and molecular systems, thereby enhancing the precision of molecular property prediction and molecular simulations. Nonetheless, as the field has been progressing to bigger and more complex architect…

Cited by 14Source ↗PDF ↗Scholar ↗
2023

Ewald-based Long-Range Message Passing for Molecular Graphs

Arthur Kosmala, Johannes Gasteiger, Nicholas Gao, Stephan Günnemann
ICML 2023poster

Neural architectures that learn potential energy surfaces from molecular data have undergone fast improvement in recent years. A key driver of this success is the Message Passing Neural Network (MPNN) paradigm. Its favorable scaling with system size partly relies upon a spatial distance limit on mes…

Cited by 38Source ↗PDF ↗code ↗Scholar ↗
2023

SubMix: Learning to Mix Graph Sampling Heuristics

Sami Abu-El-Haija, Joshua V. Dillon, Bahare Fatemi, Kyriakos Axiotis, Neslihan Bulut, Johannes Gasteiger +2
UAI 2023poster

Sampling subgraphs for training Graph Neural Networks (GNNs) is receiving much attention from the GNN community. While a variety of methods have been proposed, each method samples the graph according to its own heuristic. However, there has been little work in mixing these heuristics in an end-to-en…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2021

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
ICLR 2021poster

In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i.e. a single graph, image, or document respectively. Existing adversarial robustness certificates c…

Cited by 33Source ↗PDF ↗Scholar ↗
2021

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann
NeurIPS 2021poster

Graph neural networks that leverage coordinates via directional message passing have recently set the state of the art on multiple molecular property prediction tasks. However, they rely on atom position information that is often unavailable, and obtaining it is usually prohibitively expensive or ev…

Cited by 53Source ↗PDF ↗Scholar ↗
2021

GemNet: Universal Directional Graph Neural Networks for Molecules

Johannes Gasteiger, Florian Becker, Stephan Günnemann
NeurIPS 2021poster

Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations. Graph neural networks (GNNs) have recently shown great successes for this task, overtaking classical methods based on fixed mo…

Cited by 449Source ↗PDF ↗code ↗Scholar ↗
2021

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

Johannes Gasteiger, Marten Lienen, Stephan Günnemann
ICML 2021spotlight

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for large sets of objects. In this work we propose two effective…

Cited by 15Source ↗PDF ↗Scholar ↗
2020

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More

Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
ICML 2020poster

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input which, as our findings show, is often essential for obtaining n…

Cited by 109Source ↗PDF ↗Scholar ↗
2019

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann
ICLR 2019poster

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend. In this paper, we…

Cited by 2182Source ↗PDF ↗code ↗Scholar ↗