About
Piotr Kawa holds BSc and MSc in Computer Science and is currently PhD Student at Wroclaw University of Science and Technology. In his work he focuses on applications of machine learning in the selected aspects of information security. His research and professional interests focus on image and speech processing including topics like DeepFake detection and Text-To-Speech / Voice Conversion systems. His experience in commercial projects covers identity verification, information security (media watermarking), as well as signal processing (audio and video).
Research Interests
Education
MSc in Computer Science (Computer Security)
Wroclaw University of Science and Technology · 2020
BSc in Computer Science
Wroclaw University of Science and Technology · 2019
Publications
WSSSP-Net: Weakly Supervised Semantic Segmentation Plugin Network for Face Anti-Spoofing
2026 · WACV 2026
DeePen: Penetration Testing for Audio Deepfake Detection
2025 · arXiv 2502.20427
As Good as It KAN Get: High-Fidelity Audio Representation
2025 · CIKM 2025
Replay Attacks Against Audio Deepfake Detection
2025 · INTERSPEECH 2025
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
2024 · IJCNN 2024
A New Approach to Voice Authenticity
2024 · INTERSPEECH 2024
Defense against Adversarial Attacks on Audio DeepFake Detection
2023 · INTERSPEECH 2023
Improved DeepFake Detection Using Whisper Features
2023 · INTERSPEECH 2023
Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
2022 · *Interspeech 2022 : Human and Humanizing Speech Technology, 18-22 September 2022, Incheon, Korea.*
Verify it yourself: a note on activation functions’ influence on fast DeepFake detection
2021 · *Proceedings of the 18th International Conference on Security and Cryptography - SECRYPT*
