Dominik Hintersdorf

34 papers A* 7A 1Journal 23Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Auditing and instructing text-to-image generation models on fairness. AI Ethics Felix Friedrich, Manuel Brack, Lukas Struppek, Dominik Hintersdorf, Patrick Schramowski, Sasha Luccioni, Kristian Kersting
2025	J	`jnl`	Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed. CoRR Antoni Kowalczuk, Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2025	J	`jnl`	Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information. CoRR Lukas Struppek, Dominik Hintersdorf, Hannah Struppek, Daniel Neider, Kristian Kersting
2025	—	`—`	Understanding and Mitigating Privacy Risks in Vision and Multi-Modal Models. Dominik Hintersdorf
2024	A*	`conf`	Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks. ICLR Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2024	A	`conf`	Defending Our Privacy with Backdoors. ECAI Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
2024	J	`jnl`	Does CLIP Know My Face? J. Artif. Intell. Res. Dominik Hintersdorf, Lukas Struppek, Manuel Brack, Felix Friedrich, Patrick Schramowski, Kristian Kersting
2024	A*	`conf`	Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint). IJCAI Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
2024	J	`jnl`	Exploring the Adversarial Capabilities of Large Language Models. CoRR Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf, Kristian Kersting
2024	A*	`conf`	Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. NeurIPS Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2024	J	`jnl`	Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models. CoRR Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
2023	—	`conf`	Balancing Transparency and Risk: An Overview of the Security and Privacy Risks of Open-Source Machine Learning Models. AISoLA (Selected Papers) Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
2023	J	`jnl`	Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models. CoRR Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
2023	J	`jnl`	Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks. CoRR Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2023	J	`jnl`	Combining AI and AM - Improving approximate matching through transformer networks. Digit. Investig. Frieder Uhlig, Lukas Struppek, Dominik Hintersdorf, Thomas Göbel, Harald Baier, Kristian Kersting
2023	J	`jnl`	Defending Our Privacy With Backdoors. CoRR Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
2023	J	`jnl`	Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis. J. Artif. Intell. Res. Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
2023	J	`jnl`	Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness. CoRR Felix Friedrich, Patrick Schramowski, Manuel Brack, Lukas Struppek, Dominik Hintersdorf, Sasha Luccioni, Kristian Kersting
2023	J	`jnl`	Image Classifiers Leak Sensitive Attributes About Their Classes. CoRR Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
2023	J	`jnl`	Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data. CoRR Lukas Struppek, Martin B. Hentschel, Clifton Poth, Dominik Hintersdorf, Kristian Kersting
2023	A*	`conf`	Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis. ICCV Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2023	J	`jnl`	SEGA: Instructing Diffusion using Semantic Dimensions. CoRR Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
2023	A*	`conf`	SEGA: Instructing Text-to-Image Models using Semantic Guidance. NeurIPS Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
2022	J	`jnl`	CLIPping Privacy: Identity Inference Attacks on Multi-Modal Machine Learning Models. CoRR Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
2022	—	`conf`	Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash. FAccT Lukas Struppek, Dominik Hintersdorf, Daniel Neider, Kristian Kersting
2022	A*	`conf`	Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks. ICML Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler, Kristian Kersting
2022	J	`jnl`	Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks. CoRR Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler, Kristian Kersting
2022	J	`jnl`	Rickrolling the Artist: Injecting Invisible Backdoors into Text-Guided Image Generation Models. CoRR Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2022	J	`jnl`	The Biased Artist: Exploiting Cultural Biases via Homoglyphs in Text-Guided Image Generation Models. CoRR Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2022	J	`jnl`	The Stable Artist: Steering Semantics in Diffusion Latent Space. CoRR Manuel Brack, Patrick Schramowski, Felix Friedrich, Dominik Hintersdorf, Kristian Kersting
2022	A*	`conf`	To Trust or Not To Trust Prediction Scores for Membership Inference Attacks. IJCAI Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
2022	J	`jnl`	Transformer-Boosted Anomaly Detection with Fuzzy Hashes. CoRR Frieder Uhlig, Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
2021	J	`jnl`	Do Not Trust Prediction Scores for Membership Inference Attacks. CoRR Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
2021	J	`jnl`	Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash. CoRR Lukas Struppek, Dominik Hintersdorf, Daniel Neider, Kristian Kersting