Skip to main content
Department of Artificial Intelligence
← WrocSec.ai / AMANITA

Publications

Publications assigned to this group and public publications confirmed in the research records of its current members.

Publications: 163

  1. Precise language deception: XAI driven targeted adversarial examples with restricted knowledge

    Mateusz Gniewkowski, Paweł T Walkowiak, Marek Klonowski, Tomasz Walkowiak

    ICCS 2025 · 2025

  2. As good as it KAN get: high-fidelity audio representation

    Piotr Kawa, Piotr Syga, Patryk Marszałek, Maciej Rut, Przemysław Spurek

    2025

  3. On generalization and robustness of audio DeepFake detection

    Piotr Kawa

    2025

  4. Resilience of Named Entity Recognition models against adversarial attacks

    Paweł T. Walkowiak

    International Journal of Electronics and Telecommunications · 2025

  5. Zgłoszenie patentowe opublikowane

    Piotr Kawa, Paweł J Narolski, Filip Zagórski

    2025

  6. EmoSpeechAuth: Emotion-aware speaker verification

    Magdalena Gołębiowska, Piotr Syga

    International Speech Communication Association · 2025

  7. PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment

    Julia A Moska, Dawid Motyka, Paweł T Walkowiak, Arkadiusz Janz, Karolina Seweryn, Anna Kołos, Agnieszka Karlińska, Katarzyna Lorenc, Katarzyna Dziewulska, Maciej Chrabąszcz, Aleksandra Krasnodębska, Paula Betscher, Zofia Cieślińska, Katarzyna Kowol, Bartosz Żuk

    The 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, November 4-9 · 2025

  8. Is heterogeneous model soup tasty? A multidimensional evaluation of diverse model soups in language model alignment

    Dawid Motyka, Paweł T Walkowiak, Julia A Moska, Arkadiusz Janz, Bartosz Żuk, Karolina Seweryn

    ICCS 2025 · 2025

  9. Image-based soundtrack generation with diffusion model

    Dawid T. Wolkiewicz, Piotr Syga

    Proceedings of the 5th Polish Conference on Artificial Intelligence (PP-RAI’2024) · 2024

  10. Robustness of named entity recognition models

    Paweł T. Walkowiak

    System Dependability - Theory and Applications · 2024

  11. Large language models for data extraction in slot-filling tasks

    Marek Bazan, Dawid T Wolkiewicz, Juliusz Sarna, Tomasz Gniazdowski, Maciej E Marchwiany

    System Dependability - Theory and Applications · 2024

  12. A new approach to voice authenticity

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

    Interspeech 2024 · 2024

  13. Imperceptible QR watermarks in high-resolution videos

    Piotr Syga, Tymoteusz Lindner, Tomasz Hawro

    Proceedings of the 21st International Conference on Security and Cryptography SECRYPT 2024. Vol 1 · 2024

  14. 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

    2024

  15. Do Not Trust Me: explainability against text classification

    Mateusz Gniewkowski, Paweł T Walkowiak, Piotr Syga, Marek Klonowski, Tomasz Walkowiak

    ECAI 2023 · 2023

  16. On size hiding protocols in beeping model

    Dominik D. Bojko, Marek Klonowski, Mateusz Marciniak, Piotr Syga

    Euro-Par 2023 · 2023

  17. Efficient protective jamming in 2D SINR networks

    Dominik D. Bojko, Marek Klonowski, Mateusz Marciniak, Dariusz R Kowalski

    Euro-Par 2023 · 2023

  18. Defending network IDS against adversarial examples with continual learning

    Jędrzej Z. Kozal, Justyna Zwolińska, Marek Klonowski, Michał Woźniak

    23nd IEEE International Conference on Data Mining Workshops (ICDMW), 1–4 December 2023 Shanghai, China · 2023

  19. Improved DeepFake detection using Whisper features

    Piotr Kawa, Marcin Plata, Michał J Czuba, Piotr Szymański, Piotr Syga

    Interspeech 2023 · 2023

  20. Restrained medium access control on adversarial shared channels

    Ilya Hradovich, Marek Klonowski, Dariusz R Kowalski

    Journal of Computer and System Sciences · 2023