DROPS

Document

Security and Privacy of Large Language Models (Dagstuhl Seminar 25461)

Authors: Stephan Günnemann, Pavel Laskov, Emil Lupu, Vera Rimmer, Advije Rizvani, and Qianying Liao

Published in: Dagstuhl Reports, Volume 15, Issue 11 (2026)

Abstract

Large Language Models (LLMs) have rapidly evolved from experimental systems capable of generating simple text to powerful general-purpose tools that solve exam-level problems, assist human experts, summarize complex documents, and write code, leading to their widespread deployment in production environments to improve productivity. Their rapid adoption has outpaced scientific understanding of the associated security and privacy risks, creating a growing gap between real-world use and trust in LLM-based applications. Unlike traditional machine learning models, LLMs are inherently general-purpose, operate at unprecedented scale, are often proprietary, and are accessed through interactive dialog interfaces. This makes their behavior difficult to predict and introduces novel attack surfaces and emerging phenomena such as hallucinations. Existing methods and analyzes for conventional machine learning are insufficient to cope with these aspects. So, this Dagstuhl Seminar "Security and Privacy of Large Language Models" (25461) aimed to initiate a systematic scientific discussion on the security and privacy of language models by bringing together researchers from AI, security, privacy, and natural language processing to address three central questions: how safe and secure are LLMs in adversarial environments; to what extent users’ privacy may be at risk when interacting with LLMs; and what other categories of societal impact may arise from the rapid advancement of LLM technologies. The seminar sought to systematize existing knowledge, identify high-risk applications and prevalent attack vectors, discuss defense strategies and deployment challenges, and outline directions for future research in LLM security and privacy.

Cite as

Stephan Günnemann, Pavel Laskov, Emil Lupu, Vera Rimmer, Advije Rizvani, and Qianying Liao. Security and Privacy of Large Language Models (Dagstuhl Seminar 25461). In Dagstuhl Reports, Volume 15, Issue 11, pp. 87-113, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@Article{gunnemann_et_al:DagRep.15.11.87,
  author =	{G\"{u}nnemann, Stephan and Laskov, Pavel and Lupu, Emil and Rimmer, Vera and Rizvani, Advije and Liao, Qianying},
  title =	{{Security and Privacy of Large Language Models (Dagstuhl Seminar 25461)}},
  pages =	{87--113},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2026},
  volume =	{15},
  number =	{11},
  editor =	{G\"{u}nnemann, Stephan and Laskov, Pavel and Lupu, Emil and Rimmer, Vera and Rizvani, Advije and Liao, Qianying},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.11.87},
  URN =		{urn:nbn:de:0030-drops-274951},
  doi =		{10.4230/DagRep.15.11.87},
  annote =	{Keywords: Large Language Models, Artifician Intelligence, Security and Privacy}
}

Document

DOI: 10.4230/DagRep.12.3.141

Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132)

Authors: Martin Grohe, Stephan Günnemann, Stefanie Jegelka, and Christopher Morris

Published in: Dagstuhl Reports, Volume 12, Issue 3 (2022)

Abstract

Vectorial representations of graphs and relational structures, so-called graph embeddings, make it possible to apply standard tools from data mining, machine learning, and statistics to the graph domain. In particular, graph embeddings aim to capture important information about, both, the graph structure and available side information as a vector, to enable downstream tasks such as classification, regression, or clustering. Starting from the 1960s in chemoinformatics, research in various communities has resulted in a plethora of approaches, often with recurring ideas. However, most of the field advancements are driven by intuition and empiricism, often tailored to a specific application domain. Until recently, the area has received little stimulus from theoretical computer science, graph theory, and learning theory. The Dagstuhl Seminar 22132 "Graph Embeddings: Theory meets Practice", was aimed to gather leading applied and theoretical researchers in graph embeddings and adjacent areas, such as graph isomorphism, bio- and chemoinformatics, and graph theory, to stimulate an increased exchange of ideas between these communities.

Cite as

Martin Grohe, Stephan Günnemann, Stefanie Jegelka, and Christopher Morris. Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132). In Dagstuhl Reports, Volume 12, Issue 3, pp. 141-155, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@Article{grohe_et_al:DagRep.12.3.141,
  author =	{Grohe, Martin and G\"{u}nnemann, Stephan and Jegelka, Stefanie and Morris, Christopher},
  title =	{{Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132)}},
  pages =	{141--155},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2022},
  volume =	{12},
  number =	{3},
  editor =	{Grohe, Martin and G\"{u}nnemann, Stephan and Jegelka, Stefanie and Morris, Christopher},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.3.141},
  URN =		{urn:nbn:de:0030-drops-172727},
  doi =		{10.4230/DagRep.12.3.141},
  annote =	{Keywords: Machine Learning For Graphs, GNNs, Graph Embedding}
}

Search Results

Documents authored by Günnemann, Stephan

Security and Privacy of Large Language Models (Dagstuhl Seminar 25461)

Abstract

Cite as

Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132)

Abstract

Cite as

Thanks for your feedback!

Could not send message