headshot

Yorgos Pantis

I currently work at the National and Kapodistrian University of Athens and Archimedes/Athena RC, focusing on theory based Machine Learning models. Previously, I conducted research at DTU and CTU in Prague in the field of Optimization, and at the Athena RC and Max Planck Institute, where I specialized in Natural Language Processing. I also have a solid statistical and mathematical background acquired through master's and bachelor's studies at the University of Oxford and University of Patras. I aim to continue expanding my knowledge and pursue a research career.

  • Machine Learning
  • Large Language Models
  • Optimization
  • Combinatorials
News
  • Nov. 2024. I started a Ph.D. in the NKUA in theory-based ML, fully funded by Archimedes/Athena RC under the supervision of Christos Tzamos.

EDUCATION

  • Ph.D. in Machine Learning Nov. 2024 - Present
    National and Kapodistrian University of Athens, Department of Informatics and Telecommunications
    Ph.D. degree offers me specialized knowledge in Machine Learning, Optimization, and Statistics.
    • Supervisor: Christos Tzamos.
    • Research interests: Theory-based Machine Learning, Optimization, Learning Theory, Combinatorial.
  • M.Sc. in Statistical Science Oct. 2020 - Sep. 2021
    University of Oxford, Department of Statistics, Lincoln College
    Master degree offered me broad high-level training in Statistics and Machine Learning.
    • Courses: Statistical Machine Learning, Algorithmic Foundations of Learning, Advanced Simulation Methods, Computational Statistics, Applied Statistics, Bayes Methods, Foundations of Statistical Inference, Statistical Programming.
    • Thesis: Authorship Attribution in Ancient Greek Texts, co-supervised by Yannis Assael, George Deligiannidis, and Thea Sommerschield - Grade: 61%.
    • Grade: Merit.
  • B.Sc. in Mathematics Sep. 2016 - Aug. 2020
    University of Patras, Department of Mathematics
    Undergraduate degree offered me broad knowledge in a wide range of Mathematics and motivated me to focus on Statistics and Computer Science.
    • Division of Statistics, Probability Theory & Operational Research.
    • Thesis: Mathematical Techniques in Data Science and Machine Learning, under the supervision of Michael N. Vrahatis - Grade: 10.00/10.00.
    • Grade: 8.90/10.00 (Distinction), equivalent to first-class honours (top 1%).
  • Summer School in Economic Networks Jul. 2021
    University of Oxford
    Studied quantitative methods, applications, and impacts of network theory within Economics.
  • Summer School of Nuclear and Particle Physics Jul. 2020
    National Centre for Scientific Research Demokritos
    Worked on topics of Computer Science, Machine Learning, Nuclear, and Particle Physics - CERN.
  • Summer School in Python Jul. 2019
    University of Patras, Aristotle University of Thessaloniki, Ionian University
    Intensive summer school on advanced themes of Data Analysis and Machine Learning, using Python.

EXPERIENCE

  • Ph.D. Researcher Jul. 2024 - Present
    Archimedes - AI and Data Science Research Hub and Athena Research Center
    Working on theory based Machine Learning models through Optimization and Statistics under the supervision of Christos Tzamos.
  • Research Assistant Apr. 2024 - Jun. 2024
    Technical University of Denmark, Department of Applied Mathematics and Computer Science
    Working on Deep Learning theory, with a focus on exploring the generalization properties of overparameterized models through Optimization and Riemannian geometry under the supervision of Georgios Arvanitidis.
  • Research Assistant Apr. 2022 - Apr. 2024
    Athena Research Center, Department of Institute for the Management of Information Systems
    Working on the interface of NLP, Privacy, and Security tasks using LLMs under the supervision of Constantinos Patsakis.
  • Research Assistant Apr. 2023 - Dec. 2023
    Czech Technical University in Prague, Faculty of Electrical Engineering
    Working on the Mini-batch Stochastic Subgradient Projection method under the supervision of Vyacheslav Kungurtsev, and Jakub Mareček.
  • Research Assistant Oct. 2021 - Mar. 2022
    Max Planck Institute for Mathematics in the Sciences
    Working on the authorship attribution NLP task with a focus on Plutarch's texts using LLMs under the supervision of Ivan P. Yamshchikov, and Jürgen Jost.

PUBLICATIONS

  • The Anatomy of Deception: Measuring Technical and Human Factors of a Large-scale Phishing Campaign. Anargyros Chrysanthou, Yorgos Pantis, Constantinos Patsakis. Journal Computers & Security, 2024.
    Abstract
    Paper
    BibTeX
    In an era dominated by digital interactions, phishing campaigns have evolved to exploit not just technological vulnerabilities but also human traits. This study takes an unprecedented deep dive into large-scale phishing campaigns aimed at Meta's users, offering a dual perspective on the technical mechanics and human elements involved. Analysing data from over 25,000 victims worldwide, we highlight the nuances of these campaigns, from the intricate techniques deployed by the attackers to the sentiments and behaviours of those targeted. Unlike prior research conducted in controlled environments, this investigation capitalises on the vast, diverse, and genuine data extracted directly from active phishing campaigns, allowing for a more holistic understanding of the drivers, facilitators, and human factors. Through applying advanced computational techniques, including natural language processing and machine learning, this work unveils critical insights into the psyche of victims and the evolving tactics of modern phishers. Our analysis illustrates very poor password selection choices from the victims, with 30.27% of them picking low-complexity passwords and 58.23% reusing leaked passwords. Additionally, more than 10% exhibit strong persistence in re-victimisation by posting again to the phishing platforms of the same phishers. Finally, we reveal many correlations regarding demographics and the time periods when victims are more vulnerable during the day, as well as analyse the sentiment, emotion, and tone of text responses that they submitted, illustrating how convinced they were of the scam.
    @article{chrysanthou2024anatomy,
    title={The anatomy of deception: Measuring technical and human factors of a large-scale phishing campaign},
    author={Chrysanthou, Anargyros and Pantis, Yorgos and Patsakis, Constantinos},
    journal={Computers & Security},
    volume={140},
    pages={103780},
    year={2024},
    publisher={Elsevier}
    }
  • BERT in Plutarch's Shadows. Ivan P. Yamshchikov, Alexey Tikhonov, Yorgos Pantis, Charlotte Schubert and Jürgen Jost. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.
    Abstract
    Paper
    Code
    BibTeX
    The extensive surviving corpus of the ancient scholar Plutarch of Chaeronea (ca. 45-120 CE) also contains several texts which, according to current scholarly opinion, did not originate with him and are therefore attributed to an anonymous author Pseudo-Plutarch. These include, in particular, the work Placita Philosophorum (Quotations and Opinions of the Ancient Philosophers), which is extremely important for the history of ancient philosophy. Little is known about the identity of that anonymous author and its relation to other authors from the same period. This paper presents a BERT language model for Ancient Greek. The model discovers previously unknown statistical properties relevant to these literary, philosophical, and historical problems and can shed new light on this authorship question. In particular, the Placita Philosophorum, together with one of the other Pseudo-Plutarch texts, shows similarities with the texts written by authors from an Alexandrian context (2nd/3rd century CE).
    @inproceedings{yamshchikov2022bert,
    title={BERT in Plutarch’s Shadows},
    author={Yamshchikov, Ivan and Tikhonov, Alexey and Pantis, Yorgos and Schubert, Charlotte and Jost, J{\"u}rgen},
    booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
    pages={6071--6080},
    year={2022}
    }

HONORS & AWARDS

  • 4-year Full Scholarship Jul. 2024 - Present
    Archimedes - AI and Data Science Research Hub
    In support of my doctoral studies due to my background.
  • Full Annual Scholarship Oct. 2020 - Aug. 2021
    Bodossaki Foundation
    In support of my master's studies due to my bachelor performance.
  • Covid-19 Assistance Fund Jun. 2021
    University of Oxford, Lincoln College
    In support of my master's studies.
  • Vivian Green Student Assistance Scholarship Feb. 2021
    University of Oxford, Lincoln College
    In support of my master's studies.
  • 4-year Annual Scholarship Every Sept. 2016 - 2020
    Greek State Scholarships Foundation
    In support of my bachelor studies due to my bachelor performance.
  • 4-year Consistently in the Top 1% Every Sept. 2016 - 2020
    University of Patras, Department of Mathematics
    Classified in the top-tier of my class for the duration of my bachelor studies.
  • Ranked Second Among Admitted Students Sept. 2016
    University of Patras, Department of Mathematics
    Second place among accepted candidates for the bachelor's degree program.

SERVICE

Reviewer:

  • ICLR 2025.
  • ICML 2025.

Teaching Assistant:

  • National and Kapodistrian University of Athens, Department of Informatics and Telecommunications
    Artificial Intelligence II - Deep Learning for NLP Fall Semester 2025
    I assisted in developing lab materials focused on practical applications in the field, while also organizing and grading assignments.

Exam Proctor: Nov. 2024 – Present

  • National and Kapodistrian University of Athens, Department of Informatics and Telecommunications
    Served as an exam proctor each semester across various courses, effectively co-managing and monitoring classes to ensure smooth exam administration.

Volunteer:

  • University of Oxford, Lincoln College Sept. 2022 - Present
    Mentor undergraduate and graduate students by providing guidance on their current studies, CV preparation, and applications for graduate programs or industry opportunities.
  • Library, University of Patras Sept. 2019 - Aug. 2020
    Edited digital documents and transcribed handwritten notes to support higher education students with disabilities, including blindness, dyslexia, and other learning challenges.
  • National Technical University of Athens Oct. 2019
    Engaged with the public to explain scientific concepts and advised high school students on selecting universities that align with their interests and goals.

CONTACT

Yorgos Pantis
Ph.D. student
Archimedes/Athena RC
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens
Location:
  • Department of Informatics and Telecommunications
  • National and Kapodistrian University of Athens, Panepistimioupolis, Ilissia, GR-15784 Athens, Greece