collaborators
Showing cs.CRShow all

7 papers · 1 filter

cs.CR2026

FloatDoor: Platform-Triggered Backdoors in LLMs

Nils Loose, Jonas Sander, Felix Mächtle +1

Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has…

cs.CR2026

Steganography Without Modification: Hidden Communication via LLM Seeds

Felix Mächtle, Jonas Sander, Sebastian Berndt +3

We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or ou…

cs.CR2026

TrEEStealer: Stealing Decision Trees via Enclave Side Channels

Jonas Sander, Anja Rabich, Nick Mahling +5

Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a…

cs.CR2025

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts

Felix Mächtle, Ashwath Shetty, Jonas Sander +3

Diffusion models have significantly advanced text-to-image generation, enabling the creation of highly realistic images conditioned on textual prompts and seeds. Given the consider…

cs.CR2025

BarkBeetle: Stealing Decision Tree Models with Fault Injection

Qifan Wang, Jonas Sander, Minmin Jiang +2

Machine learning models, particularly decision trees (DTs), are widely adopted across various domains due to their interpretability and efficiency. However, as ML models become inc…

cs.CR2025

ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference

Felix Maurer, Jonas Sander, Thomas Eisenbarth

ReDash extends Dash's arithmetic garbled circuits to provide a more flexible and efficient framework for secure outsourced inference. By introducing a novel garbled scaling gadget…