Philip Sperl

According to our database, Philip Sperl authored at least 22 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Harder or Different? Understanding Generalization of Audio Deepfake Detection.

Nicolas M. Müller, Nicholas W. D. Evans, Hemlata Tak, Philip Sperl, Konstantin Böttinger

CoRR, 2024

Imbalance in Regression Datasets.

Daniel Kowatsch, Nicolas M. Müller, Kilian Tscharke, Philip Sperl, Konstantin Böttinger

CoRR, 2024

A New Approach to Voice Authenticity.

Nicolas M. Müller, Piotr Kawa, Shen Hu, Matthias Neu, Jennifer Williams, Philip Sperl, Konstantin Böttinger

CoRR, 2024

Shortcut Detection With Variational Autoencoders.

Nicolas M. Müller, Simon Roschmann, Shahbaz Khan, Philip Sperl, Konstantin Böttinger

Proceedings of the International Joint Conference on Neural Networks, 2024

MLAAD: The Multi-Language Audio Anti-Spoofing Dataset.

Nicolas M. Müller, Piotr Kawa, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Piotr Syga, Philip Sperl, Konstantin Böttinger

Proceedings of the International Joint Conference on Neural Networks, 2024

2023

Defending Neural Networks with Activation Analysis.

Philip Sperl

PhD thesis, 2023

Physical Adversarial Examples for Multi-Camera Systems.

Ana Radutoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

CoRR, 2023

Complex-valued neural networks for voice anti-spoofing.

Nicolas M. Müller, Philip Sperl, Konstantin Böttinger

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Protecting Publicly Available Data With Machine Learning Shortcuts.

Nicolas M. Müller, Maximilian Burgert, Pascal Debus, Jennifer Williams, Philip Sperl, Konstantin Böttinger

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022

Visualizing Automatic Speech Recognition - Means for a Better Understanding?

Karla Markert, Romain Parracone, Mykhailo Kulakov, Philip Sperl, Ching-Yu Kao, Konstantin Böttinger

CoRR, 2022

R2-AD2: Detecting Anomalies by Analysing the Raw Gradient.

Jan-Philipp Schulze, Philip Sperl, Ana Radutoiu, Carla Sagebiel, Konstantin Böttinger

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators.

Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

Proceedings of the International Joint Conference on Neural Networks, 2022

Anomaly Detection by Recombining Gated Unsupervised Experts.

Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

Proceedings of the International Joint Conference on Neural Networks, 2022

Assessing the Impact of Transformations on Physical Adversarial Attacks.

Paul Andrei Sava, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, 2022

2021

Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning.

Franziska Boenisch, Philip Sperl, Konstantin Böttinger

CoRR, 2021

DA3G: Detecting Adversarial Attacks by Analysing Gradients.

Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger

Proceedings of the Computer Security - ESORICS 2021, 2021

2020

Optimizing Information Loss Towards Robust Neural Networks.

Philip Sperl, Konstantin Böttinger

CoRR, 2020

A³: Activation Anomaly Analysis.

Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger

CoRR, 2020

Activation Anomaly Analysis.

Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

DLA: Dense-Layer-Analysis for Adversarial Example Detection.

Philip Sperl, Ching-Yu Kao, Peng Chen, Xiao Lei, Konstantin Böttinger

Proceedings of the IEEE European Symposium on Security and Privacy, 2020

2019

DLA: Dense-Layer-Analysis for Adversarial Example Detection.

Philip Sperl, Ching-yu Kao, Peng Chen, Konstantin Böttinger

CoRR, 2019

Side-Channel Aware Fuzzing.

Philip Sperl, Konstantin Böttinger

Proceedings of the Computer Security - ESORICS 2019, 2019