Towards personalized language models: significant advancements at the cost of emerging risks
Mateusz Gniewkowski, Paweł T Walkowiak, Marek Klonowski, Tomasz Walkowiak, Piotr Syga
ECML-PKDD 2027
2027
Profile
Piotr Syga
Assistant Professor
Piotr Syga is currently an assistant professor at the Department of Artificial Intelligence, Wroclaw University of Science and Technology. His research and professional interests include image processing and various aspects of privacy, including preserving privacy and information security in networks of severely constrained devices. In addition to his involvement in academia, he has worked with the banking sector in identity management and with industry in optimization and image processing.
Research interests
- privacy
- ad hoc networks
- biometrics
- image processing
Research groups
Education
- 0
PhD in Computer Science
Institute of Computer Science, Polish Academy of Sciences
- 0
MSc in Computer Science
Faculty of Fundamental Problems of Technology, Wrocław University of Science and Technology
Publications45
From supra to sub: a hierarchical margin-based approach for audio deepfake source tracing
Dawid T. Wolkiewicz, Piotr Syga
IEEE 2026
2026
Enhancing Speaker Verification with Whispered Speech via Post-Processing
Magdalena Gołębiowska, Piotr Syga
Communications in Computer and Information Science
2026
WSSSP-Net: Weakly supervised semantic segmentation plugin network for face anti-spoofing
Krzysztof J. Galus, Piotr Syga, Piotr Kawa
2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
2026
Faceparts: segmentation and editing of gaussian splatting avatars
Tymoteusz Zapała, Julia Farganus, Dominik Galus, Mikołaj Czachorowski, Piotr Syga, Przemysław Spurek
Raporty Katedry Sztucznej Inteligencji Politechniki Wrocławskiej. 2026, Ser. PRE, nr 22
2026
As good as it KAN get: high-fidelity audio representation
Piotr Kawa, Piotr Syga, Patryk Marszałek, Maciej Rut, Przemysław Spurek
Association for Computing Machinery
2025
Are audio DeepFake detection models polyglots?
Bartłomiej M. Marek, Piotr Kawa, Piotr Syga
W: 5th Symposium on Security and Privacy in Speech Communication, Delft, The Netherlands, 16 August 2025 / eds. Ingo Siegert [i in.]. [B.m. : b.w
2025
EmoSpeechAuth: Emotion-aware speaker verification
Magdalena Gołębiowska, Piotr Syga
International Speech Communication Association
2025
GAMER-Pong: game adjustment by monitoring emotional response
Magdalena Gołębiowska, Piotr Syga
Lecture notes in computer science
2025
2024
MLAAD: The multi-language audio anti-spoofing dataset
Piotr Kawa, Piotr Syga, Nicolas M. Müller, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Philip Sperl, Konstantin Böttinger
IEEE
2024
Imperceptible QR watermarks in high-resolution videos
Piotr Syga, Tymoteusz Lindner, Tomasz Hawro
SCITEPRESS - Science and Technology Publications, 2024]
2024
Do Not Trust Me: explainability against text classification
Mateusz Gniewkowski, Paweł T Walkowiak, Piotr Syga, Marek Klonowski, Tomasz Walkowiak
IOS Press
2023
Improved DeepFake detection using Whisper features
Piotr Kawa, Marcin Plata, Michał J Czuba, Piotr Szymański, Piotr Syga
INTERSPEECH 2023
2023
On size hiding protocols in beeping model
Dominik D. Bojko, Marek Klonowski, Mateusz Marciniak, Piotr Syga
Lecture notes in computer science
2023
SpecRNet: Towards faster and more accessible audio DeepFake detection
Piotr Kawa, Marcin Plata, Piotr Syga
Proceedings - 2022 IEEE 21st International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2022
2022
Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
Piotr Kawa, Marcin Plata, Piotr Syga
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
2022
Showing 20 of 45