29 citations · 77 across the 22 of their papers we have counts for
22 papers
You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
Ching-Yu Kao, Xinfeng Li, Shenyu Dai +4
High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are gr…
Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1
Large Language Models (LLMs) show remarkable capabilities in understanding natural language and generating complex code. However, as practitioners adopt CodeLLMs for increasingly c…
GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)
Wei Herng Choong, Jixing Liu, Ching-Yu Kao +1
Graph machine learning has been widely explored in various domains, such as community detection, transaction analysis, and recommendation systems. In these applications, anomaly de…
Replay Attacks Against Audio Deepfake Detection
Nicolas Müller, Piotr Kawa, Wei-Herng Choong +5
We show how replay attacks undermine audio deepfake detection: By playing and re-recording deepfake audio through various speakers and microphones, we make spoofed samples appear a…
DeePen: Penetration Testing for Audio Deepfake Detection
Nicolas Müller, Piotr Kawa, Adriana Stan +5
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine…
Harder or Different? Understanding Generalization of Audio Deepfake Detection
Nicolas M. Müller, Nicholas Evans, Hemlata Tak +2
Recent research has highlighted a key issue in speech deepfake detection: models trained on one set of deepfakes perform poorly on others. The question arises: is this due to the c…
Imbalance in Regression Datasets
Daniel Kowatsch, Nicolas M. Müller, Kilian Tscharke +2
For classification, the problem of class imbalance is well known and has been extensively studied. In this paper, we argue that imbalance in regression is an equally important prob…
A New Approach to Voice Authenticity
Nicolas M. Müller, Piotr Kawa, Shen Hu +4
Voice faking, driven primarily by recent advances in text-to-speech (TTS) synthesis technology, poses significant societal challenges. Currently, the prevailing assumption is that…
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
Nicolas M. Müller, Piotr Kawa, Wei Herng Choong +6
This paper presents the Multi-Language Audio Anti-Spoofing Dataset (MLAAD), version 11: a dataset of synthetic audio to train and evaluate audio deepfake detection models. It featu…
Physical Adversarial Examples for Multi-Camera Systems
Ana Răduţoiu, Jan-Philipp Schulze, Philip Sperl +1
Neural networks build the foundation of several intelligent systems, which, however, are known to be easily fooled by adversarial examples. Recent advances made these attacks possi…
Protecting Publicly Available Data With Machine Learning Shortcuts
Nicolas M. Müller, Maximilian Burgert, Pascal Debus +3
Machine-learning (ML) shortcuts or spurious correlations are artifacts in datasets that lead to very good training and test performance but severely limit the model's generalizatio…
Complex-valued neural networks for voice anti-spoofing
Nicolas M. Müller, Philip Sperl, Konstantin Böttinger
Current anti-spoofing and audio deepfake detection systems use either magnitude spectrogram-based features (such as CQT or Melspectrograms) or raw audio processed through convoluti…
Shortcut Detection with Variational Autoencoders
Nicolas M. Müller, Simon Roschmann, Shahbaz Khan +2
For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data…
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Jan-Philipp Schulze, Philip Sperl, Ana Răduţoiu +2
Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss. Samples unlike the ones seen during training cause a…
Visualizing Automatic Speech Recognition -- Means for a Better Understanding?
Karla Markert, Romain Parracone, Mykhailo Kulakov +3
Automatic speech recognition (ASR) is improving ever more at mimicking human speech processing. The functioning of ASR, however, remains to a large extent obfuscated by the complex…
Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
Franziska Boenisch, Philip Sperl, Konstantin Böttinger
An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understoo…
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
J. -P. Schulze, P. Sperl, K. Böttinger
Anomaly detection is a challenging task for machine learning algorithms due to the inherent class imbalance. It is costly and time-demanding to manually analyse the observed data,…
Optimizing Information Loss Towards Robust Neural Networks
Philip Sperl, Konstantin Böttinger
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. Th…
Anomaly Detection by Recombining Gated Unsupervised Experts
J. -P. Schulze, P. Sperl, K. Böttinger
Anomaly detection has been considered under several extents of prior knowledge. Unsupervised methods do not require any labelled data, whereas semi-supervised methods leverage some…
: Activation Anomaly Analysis
Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger
Inspired by recent advances in coverage-guided analysis of neural networks, we propose a novel anomaly detection method. We show that the hidden activation values contain informati…
DLA: Dense-Layer-Analysis for Adversarial Example Detection
Philip Sperl, Ching-Yu Kao, Peng Chen +1
In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs'…
Side-Channel Aware Fuzzing
Philip Sperl, Konstantin Böttinger
Software testing is becoming a critical part of the development cycle of embedded devices, enabling vulnerability detection. A well-studied approach of software testing is fuzz-tes…