27 citations · 110 across the 41 of their papers we have counts for
26 papers · 1 filter
Closing the Distribution Gap in Adversarial Training for LLMs
Chengzhi Hu, Jonas Dornbusch, David Lüdke +2
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerab…
Diffusion LLMs are Natural Adversaries for any LLM
David Lüdke, Tom Wollschläger, Paul Ungermann +2
We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight…
Sampling-aware Adversarial Attacks Against Large Language Models
Tim Beyer, Yan Scholten, Leo Schwinn +1
To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typ…
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
Yan Scholten, Sophie Xhonneux, Leo Schwinn +1
Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcin…
Effective Data Pruning through Score Extrapolation
Sebastian Schmidt, Prasanga Dhungel, Christoffer Löffler +3
Training advanced machine learning models demands massive datasets, resulting in prohibitive computational costs. To address this challenge, data pruning techniques identify and re…
When to retrain a machine learning model
Regol Florence, Schwinn Leo, Sprague Kyle +2
A significant challenge in maintaining real-world machine learning models is responding to the continuous and unpredictable evolution of data. Most practitioners are faced with the…
Joint Relational Database Generation via Graph-Conditional Diffusion Models
Mohamed Amine Ketata, David Lüdke, Leo Schwinn +1
Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmenting real datasets. However, most p…
Byte Pair Encoding for Efficient Time Series Forecasting
Leon Götz, Marcel Kollovieh, Stephan Günnemann +1
Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even…
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
Leo Schwinn, Yan Scholten, Tom Wollschläger +4
Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target me…
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
Yan Scholten, Stephan Günnemann, Leo Schwinn
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. Howe…
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
Marcel Kollovieh, Marten Lienen, David Lüdke +2
Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art performance in forecastin…
Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation
Björn Nieth, Thomas Altstidl, Leo Schwinn +1
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promisi…
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…
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
Leon Götz, Marcel Kollovieh, Stephan Günnemann +1
Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merg…
Efficient Adversarial Training in LLMs with Continuous Attacks
Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann +2
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most p…
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
Leo Schwinn, David Dobre, Sophie Xhonneux +2
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models.…
Raising the Bar for Certified Adversarial Robustness with Diffusion Models
Thomas Altstidl, David Dobre, Björn Eskofier +2
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training,…
FastAMI -- a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics
Kai Klede, Leo Schwinn, Dario Zanca +1
Clustering is at the very core of machine learning, and its applications proliferate with the increasing availability of data. However, as datasets grow, comparing clusterings with…
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
Leo Schwinn, Leon Bungert, An Nguyen +5
The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to e…
Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks
Leo Schwinn, René Raab, An Nguyen +2
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluat…
CLIP: Cheap Lipschitz Training of Neural Networks
Leon Bungert, René Raab, Tim Roith +2
Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulne…
Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis
Leo Schwinn, An Nguyen, René Raab +5
The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in sa…
System Design for a Data-driven and Explainable Customer Sentiment Monitor
An Nguyen, Stefan Foerstel, Thomas Kittler +8
The most important goal of customer services is to keep the customer satisfied. However, service resources are always limited and must be prioritized. Therefore, it is important to…
Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring
An Nguyen, Srijeet Chatterjee, Sven Weinzierl +3
Predictive business process monitoring (PBPM) aims to predict future process behavior during ongoing process executions based on event log data. Especially, techniques for the next…