1 code implementation • 10 Feb 2024 • Jonathan Evertz, Merlin Chlosta, Lea Schönherr, Thorsten Eisenhofer
Specifically, malicious tools can exploit vulnerabilities in the LLM itself to manipulate the model and compromise the data of other services, raising the question of how private data can be protected in the context of LLM integrations.
2 code implementations • 2 Feb 2024 • Antonio Emanuele Cinà, Francesco Villani, Maura Pintor, Lea Schönherr, Battista Biggio, Marcello Pelillo
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging.
1 code implementation • 10 Dec 2023 • Joel Frank, Franziska Herbert, Jonas Ricker, Lea Schönherr, Thorsten Eisenhofer, Asja Fischer, Markus Dürmuth, Thorsten Holz
To further understand which factors influence people's ability to detect generated media, we include personal variables, chosen based on a literature review in the domains of deepfake and fake news research.
2 code implementations • 29 Sep 2023 • Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
There is a growing interest in using Large Language Models (LLMs) as agents to tackle real-world tasks that may require assessing complex situations.
no code implementations • 9 May 2023 • David Pape, Sina Däubener, Thorsten Eisenhofer, Antonio Emanuele Cinà, Lea Schönherr
We realize that during training, the models tend to have similar predictions, indicating that the network diversity we wanted to leverage using uncertainty quantification models is not (high) enough for improvements on the model stealing task.
no code implementations • 8 Feb 2023 • Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
We evaluate the effectiveness of our approach by examining code language models in generating high-risk security weaknesses.
2 code implementations • 4 Nov 2021 • Joel Frank, Lea Schönherr
Deep generative modeling has the potential to cause significant harm to society.
1 code implementation • 10 Feb 2021 • Thorsten Eisenhofer, Lea Schönherr, Joel Frank, Lars Speckemeier, Dorothea Kolossa, Thorsten Holz
In this paper we propose a different perspective: We accept the presence of adversarial examples against ASR systems, but we require them to be perceivable by human listeners.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 21 Oct 2020 • Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, Giovanni Vigna
In a more realistic scenario, when the target audio waveform is played over the air in different rooms, VENOMAVE maintains a success rate of up to 73. 3%.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 24 May 2020 • Sina Däubener, Lea Schönherr, Asja Fischer, Dorothea Kolossa
The neural networks for uncertainty quantification simultaneously diminish the vulnerability to the attack, which is reflected in a lower recognition accuracy of the malicious target text in comparison to a standard hybrid ASR system.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • ICML 2020 • Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz
Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.
no code implementations • 5 Aug 2019 • Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa
In this paper, we demonstrate the first algorithm that produces generic adversarial examples, which remain robust in an over-the-air attack that is not adapted to the specific environment.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Aug 2018 • Lea Schönherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa
We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i. e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception.
Cryptography and Security Sound Audio and Speech Processing