Lukas Struppek

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 28

Top Topics

Image Generation

Limited Resources

Diffusion Models

Top Venues

J. Artif. Intell. Res.

Publications

Domenique Zipperling, Simeon Allmendinger, Lukas Struppek, Niklas Kühl
CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI. CoRR (2024)
Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas Kühl
CollaFuse: Collaborative Diffusion Models. CoRR (2024)
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks. ICLR (2024)
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. CoRR (2024)
Dominik Hintersdorf, Lukas Struppek, Manuel Brack, Felix Friedrich, Patrick Schramowski, Kristian Kersting
Does CLIP Know My Face? J. Artif. Intell. Res. 80 (2024)
Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf, Kristian Kersting
Exploring the Adversarial Capabilities of Large Language Models. CoRR (2024)
Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
SEGA: Instructing Text-to-Image Models using Semantic Guidance. NeurIPS (2023)
Felix Friedrich, Patrick Schramowski, Manuel Brack, Lukas Struppek, Dominik Hintersdorf, Sasha Luccioni, Kristian Kersting
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness. CoRR (2023)
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models. CoRR (2023)
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks. CoRR (2023)
Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
SEGA: Instructing Diffusion using Semantic Dimensions. CoRR (2023)
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis. J. Artif. Intell. Res. 78 (2023)
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis. ICCV (2023)
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
Image Classifiers Leak Sensitive Attributes About Their Classes. CoRR (2023)
Lukas Struppek, Martin B. Hentschel, Clifton Poth, Dominik Hintersdorf, Kristian Kersting
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data. CoRR (2023)
Svetlana Pavlitska, Christian Hubschneider, Lukas Struppek, J. Marius Zöllner
Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability. IJCNN (2023)
Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
Defending Our Privacy With Backdoors. CoRR (2023)
Frieder Uhlig, Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Transformer-Boosted Anomaly Detection with Fuzzy Hashes. CoRR (2022)
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
CLIPping Privacy: Identity Inference Attacks on Multi-Modal Machine Learning Models. CoRR (2022)
Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler, Kristian Kersting
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks. CoRR (2022)
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks. IJCAI (2022)
Svetlana Pavlitskaya, Christian Hubschneider, Lukas Struppek, J. Marius Zöllner
Balancing Expert Utilization in Mixture-of-Experts Layers Embedded in CNNs. CoRR (2022)
Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler, Kristian Kersting
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks. ICML (2022)
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
The Biased Artist: Exploiting Cultural Biases via Homoglyphs in Text-Guided Image Generation Models. CoRR (2022)
Lukas Struppek, Dominik Hintersdorf, Daniel Neider, Kristian Kersting
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash. FAccT (2022)
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Rickrolling the Artist: Injecting Invisible Backdoors into Text-Guided Image Generation Models. CoRR (2022)
Lukas Struppek, Dominik Hintersdorf, Daniel Neider, Kristian Kersting
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash. CoRR (2021)
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
Do Not Trust Prediction Scores for Membership Inference Attacks. CoRR (2021)