Philip Sperl

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 27

Top Topics

Differential Privacy

Automatic Speech Recognition

Top Venues

Publications

Nicolas M. Müller, Nicholas W. D. Evans, Hemlata Tak, Philip Sperl, Konstantin Böttinger
Harder or Different? Understanding Generalization of Audio Deepfake Detection. CoRR (2024)
Nicolas M. Müller, Piotr Kawa, Shen Hu, Matthias Neu, Jennifer Williams, Philip Sperl, Konstantin Böttinger
A New Approach to Voice Authenticity. CoRR (2024)
Nicolas M. Müller, Piotr Kawa, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Piotr Syga, Philip Sperl, Konstantin Böttinger
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset. CoRR (2024)
Daniel Kowatsch, Nicolas M. Müller, Kilian Tscharke, Philip Sperl, Konstantin Böttinger
Imbalance in Regression Datasets. CoRR (2024)
Nicolas M. Müller, Maximilian Burgert, Pascal Debus, Jennifer Williams, Philip Sperl, Konstantin Böttinger
Protecting Publicly Available Data With Machine Learning Shortcuts. CoRR (2023)
Nicolas M. Müller, Philip Sperl, Konstantin Böttinger
Complex-valued neural networks for voice anti-spoofing. CoRR (2023)
Nicolas M. Müller, Maximilian Burgert, Pascal Debus, Jennifer Williams, Philip Sperl, Konstantin Böttinger
Protecting Publicly Available Data With Machine Learning Shortcuts. BMVC (2023)
Ana Radutoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Physical Adversarial Examples for Multi-Camera Systems. CoRR (2023)
Nicolas M. Müller, Philip Sperl, Konstantin Böttinger
Complex-valued neural networks for voice anti-spoofing. INTERSPEECH (2023)
Nicolas M. Müller, Simon Roschmann, Shahbaz Khan, Philip Sperl, Konstantin Böttinger
Shortcut Detection with Variational Autoencoders. CoRR (2023)
Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators. IJCNN (2022)
Paul Andrei Sava, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Assessing the Impact of Transformations on Physical Adversarial Attacks. AISec@CCS (2022)
Jan-Philipp Schulze, Philip Sperl, Ana Radutoiu, Carla Sagebiel, Konstantin Böttinger
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient. ECML/PKDD (1) (2022)
Jan-Philipp Schulze, Philip Sperl, Ana Radutoiu, Carla Sagebiel, Konstantin Böttinger
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient. CoRR (2022)
Karla Markert, Romain Parracone, Mykhailo Kulakov, Philip Sperl, Ching-Yu Kao, Konstantin Böttinger
Visualizing Automatic Speech Recognition - Means for a Better Understanding? CoRR (2022)
Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Anomaly Detection by Recombining Gated Unsupervised Experts. IJCNN (2022)
Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
DA3G: Detecting Adversarial Attacks by Analysing Gradients. ESORICS (1) (2021)
Franziska Boenisch, Philip Sperl, Konstantin Böttinger
Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning. CoRR (2021)
J.-P. Schulze, Philip Sperl, Konstantin Böttinger
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators. CoRR (2021)
Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger
Activation Anomaly Analysis. ECML/PKDD (2) (2020)
Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger
: Activation Anomaly Analysis. CoRR (2020)
Philip Sperl, Ching-Yu Kao, Peng Chen, Xiao Lei, Konstantin Böttinger
DLA: Dense-Layer-Analysis for Adversarial Example Detection. EuroS&P (2020)
Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Anomaly Detection by Recombining Gated Unsupervised Experts. CoRR (2020)
Philip Sperl, Konstantin Böttinger
Optimizing Information Loss Towards Robust Neural Networks. CoRR (2020)
Philip Sperl, Konstantin Böttinger
Side-Channel Aware Fuzzing. CoRR (2019)
Philip Sperl, Konstantin Böttinger
Side-Channel Aware Fuzzing. ESORICS (1) (2019)
Philip Sperl, Ching-yu Kao, Peng Chen, Konstantin Böttinger
DLA: Dense-Layer-Analysis for Adversarial Example Detection. CoRR (2019)