default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDLeo Schwinn
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[i32]Tim Beyer, Jan Schuchardt, Leo Schwinn, Stephan Günnemann:
Fast Proxies for LLM Robustness Evaluation. CoRR abs/2502.10487 (2025)- [i31]Leo Schwinn, Yan Scholten, Tom Wollschläger, Sophie Xhonneux, Stephen Casper, Stephan Günnemann, Gauthier Gidel:
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives. CoRR abs/2502.11910 (2025) - [i30]Sophie Xhonneux, David Dobre, Mehrnaz Mohfakhami, Leo Schwinn, Gauthier Gidel:
A generative approach to LLM harmfulness detection with special red flag tokens. CoRR abs/2502.16366 (2025) - [i29]Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann:
Joint Out-of-Distribution Filtering and Data Discovery Active Learning. CoRR abs/2503.02491 (2025) - [i28]Tim Beyer, Sophie Xhonneux, Simon Geisler, Gauthier Gidel, Leo Schwinn, Stephan Günnemann:
LLM-Safety Evaluations Lack Robustness. CoRR abs/2503.02574 (2025) - 2024
- [j6]Philipp Dumbach
, Leo Schwinn, Tim Löhr, Phi Long Do, Bjoern M. Eskofier:
Artificial intelligence trend analysis on healthcare podcasts using topic modeling and sentiment analysis: a data-driven approach. Evol. Intell. 17(4): 2145-2166 (2024) - [j5]Sebastian Schmidt, Lukas Stappen, Leo Schwinn, Stephan Günnemann:
Generalized Synchronized Active Learning for Multi-Agent-Based Data Selection on Mobile Robotic Systems. IEEE Robotics Autom. Lett. 9(10): 8659-8666 (2024) - [c11]Thomas Altstidl, David Dobre, Arthur Kosmala, Bjoern M. Eskofier, Gauthier Gidel, Leo Schwinn:
On the Scalability of Certified Adversarial Robustness with Generated Data. NeurIPS 2024 - [c10]Leo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel, Stephan Günnemann:
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space. NeurIPS 2024 - [c9]Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn:
Efficient Adversarial Training in LLMs with Continuous Attacks. NeurIPS 2024 - [i27]Leo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel, Stephan Günnemann:
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space. CoRR abs/2402.09063 (2024) - [i26]Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann:
A Unified Approach Towards Active Learning and Out-of-Distribution Detection. CoRR abs/2405.11337 (2024) - [i25]Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn:
Efficient Adversarial Training in LLMs with Continuous Attacks. CoRR abs/2405.15589 (2024) - [i24]Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn:
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging. CoRR abs/2405.17951 (2024) - [i23]Björn Nieth, Thomas Altstidl, Leo Schwinn, Björn M. Eskofier:
Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation. CoRR abs/2406.13283 (2024) - [i22]Philipp Foth, Lukas Gosch, Simon Geisler, Leo Schwinn, Stephan Günnemann:
Relaxing Graph Transformers for Adversarial Attacks. CoRR abs/2407.11764 (2024) - [i21]Leo Schwinn, Simon Geisler:
Revisiting the Robust Alignment of Circuit Breakers. CoRR abs/2407.15902 (2024) - [i20]Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Leo Schwinn, Björn M. Eskofier:
Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision. CoRR abs/2408.09948 (2024) - [i19]Marcel Kollovieh, Marten Lienen, David Lüdke, Leo Schwinn, Stephan Günnemann:
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting. CoRR abs/2410.03024 (2024) - [i18]Yan Scholten, Stephan Günnemann, Leo Schwinn:
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models. CoRR abs/2410.03523 (2024) - [i17]Atakan Seyitoglu, Aleksei Kuvshinov, Leo Schwinn, Stephan Günnemann:
Extracting Unlearned Information from LLMs with Activation Steering. CoRR abs/2411.02631 (2024) - 2023
- [b1]Leo Schwinn:
Detektion, Quantifikation und Mitigation von Robustheitsanfälligkeiten in Tiefen Neuronalen Netzen. University of Erlangen-Nuremberg, Germany, 2023 - [j4]Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Björn M. Eskofier:
Exploring misclassifications of robust neural networks to enhance adversarial attacks. Appl. Intell. 53(17): 19843-19859 (2023) - [c8]Kai Klede, Leo Schwinn, Dario Zanca, Björn M. Eskofier:
FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics. AAAI 2023: 8317-8324 - [c7]Leo Schwinn, David Dobre, Stephan Günnemann, Gauthier Gidel:
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats. ICBINB 2023: 103-117 - [c6]Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Köferl, Christopher Mutschler, Björn M. Eskofier, Dario Zanca:
Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks. IJCNN 2023: 1-8 - [i16]Kai Klede, Leo Schwinn, Dario Zanca, Björn M. Eskofier:
FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics. CoRR abs/2305.03022 (2023) - [i15]Thomas Altstidl, David Dobre, Björn M. Eskofier, Gauthier Gidel, Leo Schwinn:
Raising the Bar for Certified Adversarial Robustness with Diffusion Models. CoRR abs/2305.10388 (2023) - [i14]Dario Zanca, Andrea Zugarini, Simon Dietz, Thomas R. Altstidl, Mark A. Turban Ndjeuha, Leo Schwinn, Bjoern M. Eskofier:
Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors. CoRR abs/2305.12380 (2023) - [i13]Leo Schwinn, David Dobre, Stephan Günnemann, Gauthier Gidel:
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats. CoRR abs/2310.19737 (2023) - 2022
- [j3]Johannes Link, Leo Schwinn, Falk Pulsmeyer, Thomas Kautz, Bjoern M. Eskofier:
xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning. Sensors 22(21): 8474 (2022) - [j2]Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca:
Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention. Trans. Mach. Learn. Res. 2022 (2022) - [c5]Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Bjoern M. Eskofier, Dario Zanca:
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification. ICML 2022: 19434-19449 - [d1]Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Köferl, Christopher Mutschler, Björn M. Eskofier, Dario Zanca:
Scaled and Translated Image Recognition (STIR). Zenodo, 2022
- [i12]Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca:
Behind the Machine's Gaze: Biologically Constrained Neural Networks Exhibit Human-like Visual Attention. CoRR abs/2204.09093 (2022) - [i11]Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Björn M. Eskofier, Dario Zanca:
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification. CoRR abs/2205.09619 (2022) - [i10]Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Köferl, Christopher Mutschler, Björn M. Eskofier, Dario Zanca:
Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks. CoRR abs/2211.10288 (2022) - [i9]Leo Schwinn, Doina Precup, Björn M. Eskofier, Dario Zanca:
Simulating Human Gaze with Neural Visual Attention. CoRR abs/2211.12100 (2022) - 2021
- [j1]An Nguyen, Stefan Foerstel, Thomas Kittler, Andrey Kurzyukov, Leo Schwinn, Dario Zanca, Tobias Hipp, Da Jun Sun, Michael Schrapp, Eva Rothgang, Björn M. Eskofier:
System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data. IEEE Access 9: 117140-117152 (2021) - [c4]Leo Schwinn, An Nguyen, René Raab, Dario Zanca, Bjoern M. Eskofier, Daniel Tenbrinck, Martin Burger:
Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks. IJCNN 2021: 1-8 - [c3]Leon Bungert, René Raab, Tim Roith, Leo Schwinn, Daniel Tenbrinck:
CLIP: Cheap Lipschitz Training of Neural Networks. SSVM 2021: 307-319 - [c2]Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Björn M. Eskofier:
Identifying untrustworthy predictions in neural networks by geometric gradient analysis. UAI 2021: 854-864 - [i8]An Nguyen, Stefan Foerstel, Thomas Kittler, Andrey Kurzyukov, Leo Schwinn, Dario Zanca, Tobias Hipp, Da Jun Sun, Michael Schrapp, Eva Rothgang, Bjoern M. Eskofier:
System Design for a Data-driven and Explainable Customer Sentiment Monitor. CoRR abs/2101.04086 (2021) - [i7]Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjoern M. Eskofier:
Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis. CoRR abs/2102.12196 (2021) - [i6]Leon Bungert, René Raab, Tim Roith, Leo Schwinn, Daniel Tenbrinck:
CLIP: Cheap Lipschitz Training of Neural Networks. CoRR abs/2103.12531 (2021) - [i5]Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Bjoern M. Eskofier:
Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks. CoRR abs/2105.10304 (2021) - 2020
- [c1]An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern M. Eskofier:
Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring. ICPM Workshops 2020: 112-123 - [i4]Leo Schwinn, Björn M. Eskofier:
Fast and Stable Adversarial Training through Noise Injection. CoRR abs/2002.10097 (2020) - [i3]An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern M. Eskofier:
Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring. CoRR abs/2010.00889 (2020) - [i2]An Nguyen, Wenyu Zhang, Leo Schwinn, Bjoern M. Eskofier:
Conformance Checking for a Medical Training Process Using Petri net Simulation and Sequence Alignment. CoRR abs/2010.11719 (2020) - [i1]Leo Schwinn, Daniel Tenbrinck, An Nguyen, René Raab, Martin Burger, Bjoern M. Eskofier:
Sampled Nonlocal Gradients for Stronger Adversarial Attacks. CoRR abs/2011.02707 (2020)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-04-14 01:34 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
