activity
20202026
most citedReliable Graph Neural Networks via Robust Aggregation

24 citations · 73 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

16 papers · 1 filter

cs.LG2025

Long-Range Graph Wavelet Networks

Filippo Guerranti, Fabrizio Forte, Simon Geisler +1

Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by mult…

cs.LG2025

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

Simon Geisler, Tom Wollschläger, M. H. I. Abdalla +3

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-c…

cs.LG2025★ 1 cited

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

Tom Wollschläger, Jannes Elstner, Simon Geisler +3

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 rema…

cs.LG2024

Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance

Dominik Fuchsgruber, Tim Poštuvan, Stephan Günnemann +1

Many applications in traffic, civil engineering, or electrical engineering revolve around edge-level signals. Such signals can be categorized as inherently directed, for example, t…

cs.LG2024

Adversarial Robustness of Graph Transformers

Philipp Foth, Lukas Gosch, Simon Geisler +2

Existing studies have shown that Message-Passing Graph Neural Networks (MPNNs) are highly susceptible to adversarial attacks. In contrast, despite the increasing importance of Grap…

cs.LG2024★ 2 cited

Spatio-Spectral Graph Neural Networks

Simon Geisler, Arthur Kosmala, Daniel Herbst +1

Spatial Message Passing Graph Neural Networks (MPGNNs) are widely used for learning on graph-structured data. However, key limitations of l-step MPGNNs are that their "receptive fi…