Towards personalized language models: significant advancements at the cost of emerging risks
M Gniewkowski, PT Walkowiak, M Klonowski, T Walkowiak, P Syga
ECML-PKDD 2027
2027
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
- 2015
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
Publications46
From supra to sub: a hierarchical margin-based approach for audio deepfake source tracing
DT Wolkiewicz, P Syga
IEEE 2026
2026
Enhancing Speaker Verification with Whispered Speech via Post-Processing
Communications in Computer and Information Science
2026
WSSSP-Net: Weakly supervised semantic segmentation plugin network for face anti-spoofing
2026 IEEE/CVF Winter Conference on Applications of Computer Vision
2026
Faceparts: segmentation and editing of gaussian splatting avatars
T Zapała, J Farganus, D Galus, M Czachorowski, P Syga, P Spurek
Raporty Katedry Sztucznej Inteligencji Politechniki Wrocławskiej. 2026, Ser. PRE (22)
2026
Performance and Efficiency Analysis of Classifiers for Sentiment and Emotion Detection
D Krutul, M Wizerkaniuk, DA Kopeć, P Syga, DT Wolkiewicz, M Pelc, …
2026 Progress in Applied Electrical Engineering
2026
As good as it KAN get: high-fidelity audio representation
P Kawa, P Syga, P Marszałek, M Rut, P Spurek
Conference paper
2025
EmoSpeechAuth: Emotion-aware speaker verification
International Speech Communication Association 5743–5747
2025
GAMER-Pong: game adjustment by monitoring emotional response
Lecture notes in computer science
2025
Image-based soundtrack generation with diffusion model
DT Wolkiewicz, P Syga
Warsaw University of Technology 438–444
2024
MLAAD: The multi-language audio anti-spoofing dataset
P Kawa, P Syga, NM Müller, WH Choong, E Casanova, E Gölge, …
Conference paper
2024
2024
Do Not Trust Me: explainability against text classification
M Gniewkowski, PT Walkowiak, P Syga, M Klonowski, T Walkowiak
Conference paper · Cited by 1
2023
Improved DeepFake detection using Whisper features
P Kawa, M Plata, MJ Czuba, P Szymański, P Syga
INTERSPEECH 2023
2023
On size hiding protocols in beeping model
DD Bojko, M Klonowski, M Marciniak, P Syga
Lecture notes in computer science
2023
Showing 20 of 46