Leo Schwinn

1. Efficient Adversarial Training in LLMs with Continuous Attacks
   2024/05/24 by Sophie Xhonneux, Alessandro Sordoni, Xhonneux, Sophie +7 · 19 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
   2024/02/14 by Leo Schwinn, David Dobre, Schwinn, Leo +7 · 17 citations
   Computer Science · #Cloud Data Security Solutions #Digital and Cyber Forensics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Security and Verification in Computing
3. Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
   2023/10/30 by Leo Schwinn, Schwinn, Leo, David Dobre +5 · 11 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Topic Modeling
4. Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
   2024/10/03 by Marcel Kollovieh, Kollovieh, Marcel, Marten Lienen +7 · 7 citations
   Computer Science · #Time Series Analysis and Forecasting #Data Stream Mining Techniques #Gaussian Processes and Bayesian Inference
5. Identifying Untrustworthy Predictions in Neural Networks by Geometric\n Gradient Analysis
   2021/02/24 by Leo Schwinn, An Nguyen, Schwinn, Leo +13 · 1 citation
   Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications
6. Fast Proxies for LLM Robustness Evaluation
   2025/02/14 by Tim Beyer, Beyer, Tim, Jan Schuchardt +5 · 2 citations
   Materials Science · #Artificial Intelligence (cs.AI) #Copper Interconnects and Reliability #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
7. FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
   2025/06/26 by Zhong, Liangyu, Joachim Sicking, Rosenthal, Fabio +9 · 3 citations
   Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications
8. Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
   2024/05/28 by Leon Götz, Marcel Kollovieh, Götz, Leon +5 · 1 citation
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Time Series Analysis and Forecasting