Get started
Author

Philip Sperl

Observed name: Sperl, Philip
ORCID: 0000-0002-7901-7168
Observed ORCID: 0000-0002-7901-7168
OpenAlex ID: A5011742469
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
2024 · Nicolas M. Müller, Piotr Kawa, et al. · International Joint Conference on Neural Networks (IJCNN) · 119
PDF
DLA: Dense-Layer-Analysis for Adversarial Example Detection
2020 · Philip Sperl, Ching-Yu Kao, et al. · IEEE European Symposium on Security and Privacy · 49
PDF
Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
2021 · Boenisch, Franziska, Sperl, Philip, et al. · arXiv (Cornell University) · 29
PDF
Harder or Different? Understanding Generalization of Audio Deepfake Detection
2024 · Nicolas M. Müller, Nicholas Evans, et al. · Interspeech (USB) · 26
PDF
Complex-valued neural networks for voice anti-spoofing
2023 · Nicolas M. Müller, Philip Sperl, et al. · Interspeech (USB) · 25
PDF
Replay Attacks Against Audio Deepfake Detection
2025 · Nicolas Müller, Piotr Kawa, et al. · Interspeech (USB) · 20
PDF
Assessing the Impact of Transformations on Physical Adversarial Attacks
2022 · Paul Andrei Sava, Jan-Philipp Schulze, et al. · ACM Workshop on Artificial Intelligence and Security (AISec) · 14
A New Approach to Voice Authenticity
2024 · Nicolas M. Müller, Piotr Kawa, et al. · Interspeech (USB) · 12
PDF
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
2022 · Jan-Philipp Schulze, Philip Sperl, et al. · International Joint Conference on Neural Networks (IJCNN) · 11
PDF
Shortcut Detection With Variational Autoencoders
2024 · Nicolas M. Müller, Simon Roschmann, et al. · International Joint Conference on Neural Networks (IJCNN) · 8
PDF
Imbalance in Regression Datasets
2024 · Kowatsch, Daniel, Müller, Nicolas M., et al. · arXiv (Cornell University) · 8
PDF
DA3G: Detecting Adversarial Attacks by Analysing Gradients
2021 · Jan-Philipp Schulze, Philip Sperl, et al. · Lecture notes in computer science · 8
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
2023 · Jan-Philipp Schulze, Philip Sperl, et al. · Lecture notes in computer science · 6
PDF
Anomaly Detection by Recombining Gated Unsupervised Experts
2022 · Jan-Philipp Schulze, Philip Sperl, et al. · International Joint Conference on Neural Networks (IJCNN) · 6
PDF
Optimizing Information Loss Towards Robust Neural Networks
2020 · Philip Sperl, Konstantin Böttinger · 6
PDF
Visualizing Automatic Speech Recognition – Means for a Better Understanding?
2021 · Karla Markert, Romain Parracone, et al. · 5
PDF
Physical Adversarial Examples for Multi-Camera Systems
2023 · Răduţoiu, Ana, Schulze, Jan-Philipp, et al. · arXiv (Cornell University) · 4
PDF
GRASPED: Graph Anomaly Detection Using Autoencoder with Spectral Encoder and Decoder
2025 · Wei Herng Choong, Jixing Liu, et al. · Frontiers in artificial intelligence and applications · 3
DeePen: Penetration Testing for Audio Deepfake Detection
2025 · Müller, Nicolas, Kawa, Piotr, et al. · arXiv (Cornell University) · 3
PDF
Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
2026 · Maximilian Wendlinger, Daniel Kowatsch, et al. · IEEE European Symposium on Security and Privacy · 2
You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
2026 · Kao, Ching-Yu, Li, Xinfeng, et al. · arXiv (Cornell University) · 2
PDF
Demo: CARLA-based Adversarial Attack Assessment on Autonomous Vehicles
2024 · Zirui Lan, Wei Herng Choong, et al. · Symposium on Vehicle Security and Privacy (VehicleSec) · 1
PDF
GRASPED: Graph Anomaly Detection Using Autoencoder with Spectral Encoder and Decoder
2025 · Choong, Wei Herng, Liu, Jixing, et al. · Fraunhofer-Publica (Fraunhofer-Gesellschaft)
Protecting Publicly Available Data With Machine Learning Shortcuts
2023 · Müller, Nicolas M., Burgert, Maximilian, et al. · ePrints Soton (University of Southampton)
PDF
A 3 : Activation Anomaly Analysis.
2020 · Philip Sperl, Jan-Philipp Schulze, et al.
Works count: 33
Citation count: 370
H-index: 9
I10-index: 9
Year
Topic
Type