activity
20242026
collaborators

8 papers

cs.CR2026

You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models

Richard A. Dubniczky, Bertalan Borsos, Tamas Bisztray +1

The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlooked security risks. Beyond PDFs, these…

cs.CR2025

The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution

Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky +2

In this paper, we present the first large-scale study exploring whether JavaScript code generated by Large Language Models (LLMs) can reveal which model produced it, enabling relia…

cs.CR2025

Sustaining Cyber Awareness: The Long-Term Impact of Continuous Phishing Training and Emotional Triggers

Rebeka Toth, Richard A. Dubniczky, Olga Limonova +1

Phishing constitutes more than 90\% of successful cyberattacks globally, remaining one of the most persistent threats to organizational security. Despite organizations tripling the…

cs.LG2025

I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution

Tamas Bisztray, Bilel Cherif, Richard A. Dubniczky +6

Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identi…

cs.CR2025

DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response

Bilel Cherif, Tamas Bisztray, Richard A. Dubniczky +3

Digital Forensics and Incident Response (DFIR) involves analyzing digital evidence to support legal investigations. Large Language Models (LLMs) offer new opportunities in DFIR tas…

cs.CR2025

CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection

Richard A. Dubniczky, Krisztofer Zoltán Horvát, Tamás Bisztray +3

Identifying vulnerabilities in source code is crucial, especially in critical software components. Existing methods such as static analysis, dynamic analysis, formal verification,…