12 papers
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
Tobias Braun, Nils Loose, Alexander Herzog +4
Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust…
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…
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Gianluca Barmina, Federico Torrielli, Sven Harms +7
Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpf…
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…
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…
DRAMatic Speedup: Accelerating HE Operations on a Processing-in-Memory System
Niklas Klinger, Jonas Sander, Peterson Yuhala +2
Homomorphic encryption (HE) is a promising technology for confidential cloud computing, as it allows computations on encrypted data. However, HE is computationally expensive and of…
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…
AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution
Felix Mächtle, Nils Loose, Jan-Niclas Serr +2
Symbolic execution is a powerful technique for software testing, but suffers from limitations when encountering external functions, such as native methods or third-party libraries.…
Provable one-poison backdoor attacks on linear models and ReLU neural networks
Thorsten Peinemann, Paula Arnold, Sebastian Berndt +2
Backdoor poisoning attacks are a threat to machine learning models that are trained on data collected from untrusted sources; these attacks enable attackers to inject malicious beh…
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…
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…
Silenzio: Secure Non-Interactive Outsourced MLP Training
Jonas Sander, Thomas Eisenbarth
Outsourcing ML training to cloud-service-providers presents a compelling opportunity for resource constrained clients, while it simultaneously bears inherent privacy risks. We intr…