27 citations · 110 across the 41 of their papers we have counts for
11 papers · 1 filter
Extracting Unlearned Information from LLMs with Activation Steering
Atakan Seyitoğlu, Aleksei Kuvshinov, Leo Schwinn +1
An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or c…
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…
Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision
Dario Zanca, Andrea Zugarini, Simon Dietz +4
Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we…
Revisiting the Robust Alignment of Circuit Breakers
Leo Schwinn, Simon Geisler
Over the past decade, adversarial training has emerged as one of the few reliable methods for enhancing model robustness against adversarial attacks [Szegedy et al., 2014, Madry et…
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…
A Unified Approach Towards Active Learning and Out-of-Distribution Detection
Sebastian Schmidt, Leonard Schenk, Leo Schwinn +1
When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled…
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.…