140 citations · 244 across the 21 of their papers we have counts for
21 papers
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Lukas Struppek, Adam Gleave, Kellin Pelrine
As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight mo…
Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information
Lukas Struppek, Dominik Hintersdorf, Hannah Struppek +2
Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference lat…
CollaFuse: Collaborative Diffusion Models
Simeon Allmendinger, Domenique Zipperling, Lukas Struppek +1
In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffu…
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting +2
Diffusion models (DMs) produce very detailed and high-quality images. Their power results from extensive training on large amounts of data, usually scraped from the internet withou…
CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI
Domenique Zipperling, Simeon Allmendinger, Lukas Struppek +1
In the landscape of generative artificial intelligence, diffusion-based models present challenges for socio-technical systems in data requirements and privacy. Traditional approach…
Exploring the Adversarial Capabilities of Large Language Models
Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf +1
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for bot…
Defending Our Privacy With Backdoors
Dominik Hintersdorf, Lukas Struppek, Daniel Neider +1
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can ext…
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalizati…
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
Lukas Struppek, Martin B. Hentschel, Clifton Poth +2
Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent dur…
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both rese…
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich +3
Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising conc…
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Felix Friedrich, Manuel Brack, Lukas Struppek +4
Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly da…
SEGA: Instructing Text-to-Image Models using Semantic Guidance
Manuel Brack, Felix Friedrich, Dominik Hintersdorf +3
Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot ge…
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided i…
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich +3
Models for text-to-image synthesis, such as DALL-E~2 and Stable Diffusion, have recently drawn a lot of interest from academia and the general public. These models are capable of p…
Does CLIP Know My Face?
Dominik Hintersdorf, Lukas Struppek, Manuel Brack +3
With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have…
Combining AI and AM - Improving Approximate Matching through Transformer Networks
Frieder Uhlig, Lukas Struppek, Dominik Hintersdorf +3
Approximate matching (AM) is a concept in digital forensics to determine the similarity between digital artifacts. An important use case of AM is the reliable and efficient detecti…
Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability
Svetlana Pavlitska, Christian Hubschneider, Lukas Struppek +1
Sparsely-gated Mixture of Expert (MoE) layers have been recently successfully applied for scaling large transformers, especially for language modeling tasks. An intriguing side eff…
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia +2
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's…
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting
Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model. Knowing this may indeed lead to a privacy breach. Most MIAs, ho…
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
Lukas Struppek, Dominik Hintersdorf, Daniel Neider +1
Apple recently revealed its deep perceptual hashing system NeuralHash to detect child sexual abuse material (CSAM) on user devices before files are uploaded to its iCloud service.…