5 papers
Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?
Teodor Chiaburu, Franz Motzkus, Frank Haußer +1
Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex features learned by a model into m…
Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models
Franz Motzkus, Sebastian Bernhard
The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavio…
CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations
Franz Motzkus, Christian Hellert, Ute Schmid
Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at th…
Locally Testing Model Detections for Semantic Global Concepts
Franz Motzkus, Georgii Mikriukov, Christian Hellert +1
Ensuring the quality of black-box Deep Neural Networks (DNNs) has become ever more significant, especially in safety-critical domains such as automated driving. While global concep…
The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus +1
Adversarial attacks (AAs) pose a significant threat to the reliability and robustness of deep neural networks. While the impact of these attacks on model predictions has been exten…