Lukas Struppek

PhD thesis, 2025

2024

Does CLIP Know My Face?

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2024

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation.

[BibT_eX]

[DOI]

CoRR, 2024

CollaFuse: Collaborative Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

Exploring the Adversarial Capabilities of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint).

[BibT_eX]

[DOI]

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Collafuse: Navigating Limited Resources and Privacy in Collaborative Generative AI.

[BibT_eX]

[DOI]

Proceedings of the 32nd European Conference on Information Systems, 2024

Defending Our Privacy with Backdoors.

[BibT_eX]

[DOI]

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2023

Combining AI and AM - Improving approximate matching through transformer networks.

[BibT_eX]

[DOI]

Digit. Investig., 2023

Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data.

[BibT_eX]

[DOI]

CoRR, 2023

Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models.

[BibT_eX]

[DOI]

CoRR, 2023

Image Classifiers Leak Sensitive Attributes About Their Classes.

[BibT_eX]

[DOI]

CoRR, 2023

Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness.

[BibT_eX]

[DOI]

CoRR, 2023

SEGA: Instructing Diffusion using Semantic Dimensions.

[BibT_eX]

[DOI]

CoRR, 2023

Balancing Transparency and Risk: An Overview of the Security and Privacy Risks of Open-Source Machine Learning Models.

[BibT_eX]

[DOI]

Proceedings of the Bridging the Gap Between AI and Reality, 2023

SEGA: Instructing Text-to-Image Models using Semantic Guidance.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability.

[BibT_eX]

[DOI]

Svetlana Pavlitska

Christian Hubschneider

J. Marius Zöllner

Proceedings of the International Joint Conference on Neural Networks, 2023

Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

Rickrolling the Artist: Injecting Invisible Backdoors into Text-Guided Image Generation Models.

[BibT_eX]

[DOI]

CoRR, 2022

The Biased Artist: Exploiting Cultural Biases via Homoglyphs in Text-Guided Image Generation Models.

[BibT_eX]

[DOI]

CoRR, 2022

CLIPping Privacy: Identity Inference Attacks on Multi-Modal Machine Learning Models.

[BibT_eX]

[DOI]

CoRR, 2022

Transformer-Boosted Anomaly Detection with Fuzzy Hashes.

[BibT_eX]

[DOI]

CoRR, 2022

Balancing Expert Utilization in Mixture-of-Experts Layers Embedded in CNNs.

[BibT_eX]

[DOI]

Svetlana Pavlitskaya

Christian Hubschneider

J. Marius Zöllner

CoRR, 2022

To Trust or Not To Trust Prediction Scores for Membership Inference Attacks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks.

[BibT_eX]

[DOI]

Antonio De Almeida Correia

Antonia Adler

Proceedings of the International Conference on Machine Learning, 2022

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash.

[BibT_eX]

[DOI]

Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

2021

Do Not Trust Prediction Scores for Membership Inference Attacks.

[BibT_eX]

[DOI]