AI Safety

Sztuczna inteligencja

Understanding the nature of artificial intelligence is one of the grand challenges of our times. This challenge, together with safe deployment of AI systems, is at the core of our research on the mathematical foundations of machine learning. We engineer learning algorithms and develop data representations supporting AI interpretability, explainability, and trustworthiness. We design experiments and methods to unpack black boxes, including generative AI and large language models (LLMs). We care about AI ethics, AI evolution, and its security.

AI in Deep Brain Stimulation (DBS) and Tractography, our moonshot! During the deep brain stimulation surgery for Parkinson’s disease, the goal is to place the permanent stimulating electrode into an area of the brain that becomes pathologically hyperactive. This area is small and deep within the brain, so the main challenge is its precise localization. At NASK, we have developed a technology that calculates the localization and significantly (two or three times!) reduces the open-brain surgery time.

But that is not all. Neurosurgeries impose risks given the delicate nature of the brain tissue. Preoperative planning is critical. To address that challenge, we have also developed trustworthy AI-based methods identifying the location of eloquent brain regions and the nerve pathways leading to them.

#AI in Deep Brain Stimulation

 

In the field of natural language processing (#NLProc), we are looking for new, explainable representations of language data and investigating the relationships between grammar and semantics, particularly in tasks involving identifying and classifying atypical, potentially harmful content (such as hate speech, pornography, and misinformation). We prioritize models tailored to the problem rather than just trendy ones, resulting from a deep understanding of the data, its structures, or textual style. We are looking for the sentiment and a range of styles that can be encapsulated within algorithmic frameworks. We summarize, analyze, and anonymize. We explore internet content, legal documents, sales language, ChatGPT style, and literary parodies. We track and describe patterns—as both a classification tool and a linguistic object.

#StyloMetrix.

 

Biometrics and computer vision have a long history with us, including technologies for iris vitality identification. We design biometric authentication systems and address a wide scope of biometrics security. We study and develop deep learning methods, including those based on the transformer and generative models, signal and image processing algorithms that support deepfake detection, monitoring systems, and mobile devices.

 

Data science means machine learning algorithms, global optimization, and heuristic methods. We create decision support systems, data mining technologies, and data-driven forecasting algorithms. We study social networks focusing on cyber security issues, disinformation, and illegal content propagation.

 

We are working on:

  • Detection and analysis of harmful online content
  • Processing and classification of legal and formal documents
  • Mathematical foundations of artificial intelligence and data analysis
  • Analysis of machine learning and machine intelligence processes
  • Learning and data representation engineering
  • Safety, hygiene and transparency of AI (OSH-AI)
  • Ethics and evolution of AI
  • Multimedia data analysis
  • Applications of AI in cybersecurity, medicine, biometrics, digital humanities and social research
  • Digital humanities

Selected Publications

Articles

Antonina Krajewska, Ewa Niewiadomska-Szynkiewicz, "Efficient Data Completion and Augmentation", 2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA), DSAA 2024, 2024, 1-10.
Mateusz Koryciński, Konrad Ciecierski, “Tractography methods in preoperative neurosurgical planning”, Journal of Telecommunications and Information Technology, 3, 2021, 78–85.
Weronika Gutfeter, Andrzej Pacut, "Proxy Embeddings for Face Identification among Multi-Pose Templates", Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020, Vol. 5, 2020, 513-520.
Konrad Ciecierski, Tomasz S. Mandat, "Classification of DBS microelectrode recordings using a residual neural network with attention in the temporal domain", Neural Networks, 170, 2024, 18-31.
Victor Mandat, Pawel R. Zdunek, Bartosz Krolicki, Krzysztof Szalecki, Henryk M. Koziara, Konrad Ciecierski, Tomasz S. Mandat, "Periaqueductal/periventricular gray deep brain stimulation for the treatment of neuropathic facial pain", Frontiers in Neurology, 14, 2023, 1-8.
Tomasz Lehmann, Andrzej Pacut, Piotr Paziewski, “Face and silhouette based age estimation for child detection system”, Communication Papers of the of the 17th Conference on Computer Science and Intelligence Systems, 32, 2022, 39–43.
Weronika Gutfeter, Andrzej Pacut, “Fusion of Depth and Thermal Imaging for People Detection”, Journal of Telecommunications and Information Technology, 4, 2021, 53–60.
Kamila Lis, Wojciech Szynkiewicz, Ewa Niewiadomska-Szynkiewicz, Konrad Ciecierski, "Wykrywanie anomalii w zachowaniu robota usługowego z wykorzystaniem sieci LSTM", 16. Krajowa Konferencja Robotyki – Postępy robotyki, 197, 2022, 211–222.
Mohammadreza Azimi, Seyed Ahmad Rasoulinejad, Andrzej Pacut, “Age dependency of the diabetes effects on the iris recognition systems performance evaluation results”, Biomedical Engineering / Biomedizinische Technik, 66(1), 2021, 11–19.
Kamila Lis, Mateusz Koryciński, Konrad Ciecierski, "Classification of masked image data", PLOS One, 16(7), 2021, e0254181.
Mohammadreza Azimi, Andrzej Pacut, “The Effects of Social Issues and Human Factors on the Reliability of Biometric Systems: A Review”, Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Systems and Applications. IntelliSys 2020. Advances in Intelligent Systems and Computing, vol. 1251. Springer, Cham, 2020, 103-110.
Mohammadreza Azimi, Andrzej Pacut, “Investigation into the reliability of facial recognition systems under the simultaneous influences of mood variation and makeup”, Computers and Electrical Engineering, 85, 2020, 1–15.
Ewelina Bartuzi, Mateusz Trokielewicz, "Multispectral hand features for secure biometric authentication systems. Concurrency and Computation", Concurrency and Computation: Practice and Experience, 33(18), 2021, 6471.
Inez Okulska, Anna Kołos, Krzysztof Skibski, "Gra w klasy, czyli analiza lingwistycznych cech idiopoetyki na marginesie automatycznej klasyfikacji utworów poetyckich i ich parodii", Biuletyn Polskiego Towarzystwa Językoznawczego, LXXIX (79), 2023, 239-257.
Inez Okulska, Anna Kołos, "Morfosyntaktyczna analiza przykładów mowy nienawiści zablokowanych przez moderatorów serwisu Wykop.pl", Tertium, ;8(2), 2023, 54–71.
Anna Kołos, Inez Okulska, Kinga Głąbińska, Agnieszka Karlinska, Emilia Wiśnios, Paweł Ellerik, Andrzej Prałat, "BAN-PL: A Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl Web Service", In: Calzolari N, Kan M-Y, Hoste V, Lenci A, Sakti S, Xue N, eds. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italia: ELRA and ICCL, 2024, 2107–2118.
Daniel Ziembicki, Karolina Seweryn, Anna Wróblewska, "Polish Natural Language Inference and Factivity – an Expert-based Dataset and Benchmarks", Natural Language Engineering, 30(2), 2023, 385–416.
Anna Wróblewska, Bartosz Pieliński, Karolina Seweryn, Sylwia Sysko-Romańczuk, Karol Saputa, Aleksandra Wichrowska, Hanna Schreiber, "Automating the Analysis of Institutional Design in International Agreements", Computational Science – ICCS 2023, Lecture Notes in Computer Science, vol. 10475, red. Jiří Mikyška, Clélia de Mulatier, Maciej Paszynski, Valeria V. Krzhizhanovskaya, Jack J. Dongarra, Peter M.A. Sloot, 2023, Springer, Cham.
Agnieszka Karlinska, Cezary Rosiński, Marek Kubis, Patryk Hubar, Jan Wieczorek, "Using Bibliodata LODification to Create Metadata-Enriched Literary Corpora in Line with FAIR Principles", In: Calzolari N, Kan M-Y, Hoste V, Lenci A, Sakti S, Xue N, eds. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italia: ELRA and ICCL, 2024, 17271–17284.
Dominik Filipiak, Andrzej Zapała, Piotr Tempczyk, Anna Fensel, Marek Cygan, "Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding", IEEE Access., 2024:1, 2024, 37744-37756.