208 citations · 245 across the 11 of their papers we have counts for
14 papers
Safety of Latent Communication in Multi-Agent Systems
Muhammad Huzaifa, Sina Mavali, Thorsten Eisenhofer
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-ba…
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Muhammad Huzaifa, Lea Schönherr, Thorsten Eisenhofer
Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most…
No More, No Less: Task Alignment in Terminal Agents
Sina Mavali, David Pape, Jonathan Evertz +5
Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in…
Chasing Shadows: Pitfalls in LLM Security Research
Jonathan Evertz, Niklas Risse, Nicolai Neuer +12
Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of re…
Prompt Obfuscation for Large Language Models
David Pape, Sina Mavali, Thorsten Eisenhofer +1
System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal o…
Whispers in the Machine: Confidentiality in Agentic Systems
Jonathan Evertz, Merlin Chlosta, Lea Schönherr +1
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrati…
A Representative Study on Human Detection of Artificially Generated Media Across Countries
Joel Frank, Franziska Herbert, Jonas Ricker +5
AI-generated media has become a threat to our digital society as we know it. These forgeries can be created automatically and on a large scale based on publicly available technolog…
On the Limitations of Model Stealing with Uncertainty Quantification Models
David Pape, Sina Däubener, Thorsten Eisenhofer +2
Model stealing aims at inferring a victim model's functionality at a fraction of the original training cost. While the goal is clear, in practice the model's architecture, weight d…
No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Thorsten Eisenhofer, Erwin Quiring, Jonas Möller +3
The number of papers submitted to academic conferences is steadily rising in many scientific disciplines. To handle this growth, systems for automatic paper-reviewer assignments ar…
Dompteur: Taming Audio Adversarial Examples
Thorsten Eisenhofer, Lea Schönherr, Joel Frank +3
Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmle…
VenoMave: Targeted Poisoning Against Speech Recognition
Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer +4
Despite remarkable improvements, automatic speech recognition is susceptible to adversarial perturbations. Compared to standard machine learning architectures, these attacks are si…
Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers
Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer +3
Voice assistants like Amazon's Alexa, Google's Assistant, or Apple's Siri, have become the primary (voice) interface in smart speakers that can be found in millions of households.…
Leveraging Frequency Analysis for Deep Fake Image Recognition
Joel Frank, Thorsten Eisenhofer, Lea Schönherr +3
Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements ha…
Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems
Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler +2
Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio si…