Norbert Tihanyi

58 papers A 1B 2C 1Misc 5Journal 38Unranked 10
YearRankTypeTitle / Venue / Authors
2026 J jnl
From prompt injections to protocol exploits: Threats in LLM-powered AI agents workflows.
ICT Express
Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda, Leandros Maglaras, Abderrahmane Lakas, Mérouane Debbah
2025 C conf
A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification.
AST
Norbert Tihanyi, Yiannis Charalambous, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro
2025 Misc conf
CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs Towards CWE Detection.
TASE
Richard A. Dubniczky, Krisztofer Zoltán Horvát, Tamás Bisztray, Mohamed Amine Ferrag, Lucas C. Cordeiro, Norbert Tihanyi
2025 J jnl
CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection.
CoRR
Richard A. Dubniczky, Krisztofer Zoltán Horvát, Tamás Bisztray, Mohamed Amine Ferrag, Lucas C. Cordeiro, Norbert Tihanyi
2025 — conf
DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response.
ICONIP (1)
Bilel Cherif, Tamás Bisztray, Richard A. Dubniczky, Aaesha Aldahmani, Saeed Alshehhi, Norbert Tihanyi
2025 J jnl
DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response.
CoRR
Bilel Cherif, Tamás Bisztray, Richard A. Dubniczky, Aaesha Aldahmani, Saeed Alshehhi, Norbert Tihanyi
2025 — conf
ESBMC v7.7: Efficient Concurrent Software Verification with Scheduling, Incremental SMT and Partial Order Reduction - (Competition Contribution).
TACAS (3)
Tong Wu, Xianzhiyu Li, Edoardo Manino, Rafael Sá Menezes, Mikhail R. Gadelha, Shale Xiong, Norbert Tihanyi, Pavlos Petoumenos, Lucas C. Cordeiro
2025 J jnl
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review.
CoRR
Mohamed Amine Ferrag, Norbert Tihanyi, Mérouane Debbah
2025 J jnl
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows.
CoRR
Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda, Leandros Maglaras, Mérouane Debbah
2025 J jnl
How secure is AI-generated code: a large-scale comparison of large language models.
Empir. Softw. Eng.
Norbert Tihanyi, Tamás Bisztray, Mohamed Amine Ferrag, Ridhi Jain, Lucas C. Cordeiro
2025 — conf
I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution.
AISec@CCS
Tamás Bisztray, Bilel Cherif, Richard A. Dubniczky, Nils Gruschka, Bertalan Borsos, Mohamed Amine Ferrag, Attila Kovács, Vasileios Mavroeidis, Norbert Tihanyi
2025 J jnl
I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution.
CoRR
Tamás Bisztray, Bilel Cherif, Richard A. Dubniczky, Nils Gruschka, Bertalan Borsos, Mohamed Amine Ferrag, Attila Kovács, Vasileios Mavroeidis, Norbert Tihanyi
2025 J jnl
Reasoning Beyond Limits: Advances and Open Problems for LLMs.
CoRR
Mohamed Amine Ferrag, Norbert Tihanyi, Mérouane Debbah
2025 J jnl
Reasoning beyond limits: Advances and open problems for LLMs.
ICT Express
Mohamed Amine Ferrag, Norbert Tihanyi, Mérouane Debbah
2025 J jnl
SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection With LLMs?
IEEE Trans. Software Eng.
Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi, Ridhi Jain, Diana Maimut, Fatima Alwahedi, Thierry Lestable, Narinderjit Singh Thandi, Abdechakour Mechri, Mérouane Debbah, Lucas C. Cordeiro
2025 B conf
Sustaining Cyber Awareness: The Long-Term Impact of Continuous Phishing Training and Emotional Triggers.
IEEE Big Data
Rebeka Tóth, Richard A. Dubniczky, Olga Limonova, Norbert Tihanyi
2025 J jnl
Sustaining Cyber Awareness: The Long-Term Impact of Continuous Phishing Training and Emotional Triggers.
CoRR
Rebeka Tóth, Richard A. Dubniczky, Olga Limonova, Norbert Tihanyi
2025 J jnl
The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution.
CoRR
Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky, Mohamed Amine Ferrag, Tamás Bisztray
2025 — conf
VO-GCSE: Verification Optimization through Global Common Subexpression Elimination.
SIGSOFT FSE Companion
Rafael Sá Menezes, Norbert Tihanyi, Ridhi Jain, Alexander Levin, Rosiane de Freitas, Lucas C. Cordeiro
2025 J jnl
Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview.
CoRR
Norbert Tihanyi, Tamás Bisztray, Mohamed Amine Ferrag, Bilel Cherif, Richard A. Dubniczky, Ridhi Jain, Lucas C. Cordeiro
2025 J jnl
You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models.
CoRR
Richard A. Dubniczky, Bertalan Borsos, Norbert Tihanyi
2024 Misc conf
CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge.
CSR
Norbert Tihanyi, Mohamed Amine Ferrag, Ridhi Jain, Tamás Bisztray, Mérouane Debbah
2024 J jnl
CyberMetric: A Benchmark Dataset for Evaluating Large Language Models Knowledge in Cybersecurity.
CoRR
Norbert Tihanyi, Mohamed Amine Ferrag, Ridhi Jain, Mérouane Debbah
2024 J jnl
D(HE)at: A Practical Denial-of-Service Attack on the Finite Field Diffie-Hellman Key Exchange.
IEEE Access
Szilárd Pfeiffer, Norbert Tihanyi
2024 J jnl
Do Neutral Prompts Produce Insecure Code? FormAI-v2 Dataset: Labelling Vulnerabilities in Code Generated by Large Language Models.
CoRR
Norbert Tihanyi, Tamás Bisztray, Mohamed Amine Ferrag, Ridhi Jain, Lucas C. Cordeiro
2024 B conf
Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence.
IEEE Big Data
Norbert Tihanyi, Tamás Bisztray, Richard A. Dubniczky, Rebeka Tóth, Bertalan Borsos, Bilel Cherif, Ridhi Jain, Lajos Muzsai, Mohamed Amine Ferrag, Ryan Marinelli, Lucas C. Cordeiro, Mérouane Debbah, Vasileios Mavroeidis, Audun Jøsang
2024 J jnl
Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence.
CoRR
Norbert Tihanyi, Tamás Bisztray, Richard A. Dubniczky, Rebeka Tóth, Bertalan Borsos, Bilel Cherif, Mohamed Amine Ferrag, Lajos Muzsai, Ridhi Jain, Ryan Marinelli, Lucas C. Cordeiro, Mérouane Debbah
2024 — conf
ESBMC v7.4: Harnessing the Power of Intervals - (Competition Contribution).
TACAS (3)
Rafael Sá Menezes, Mohannad Aldughaim, Bruno Farias, Xianzhiyu Li, Edoardo Manino, Fedor Shmarov, Kunjian Song, Franz Brauße, Mikhail R. Gadelha, Norbert Tihanyi, Konstantin Korovin, Lucas C. Cordeiro
2024 J jnl
From 5G to 6G Networks: A Survey on AI-Based Jamming and Interference Detection and Mitigation.
IEEE Open J. Commun. Soc.
Poonam Lohan, Burak Kantarci, Mohamed Amine Ferrag, Norbert Tihanyi, Yi Shi
2024 J jnl
Generative AI and Large Language Models for Cyber Security: All Insights You Need.
CoRR
Mohamed Amine Ferrag, Fatima Alwahedi, Ammar Battah, Bilel Cherif, Abdechakour Mechri, Norbert Tihanyi
2024 A conf
JCWIT: A Correctness-Witness Validator for Java Programs Based on Bounded Model Checking.
ISSTA
Zaiyu Cheng, Tong Wu, Peter Schrammel, Norbert Tihanyi, Eddie B. de Lima Filho, Lucas C. Cordeiro
2024 J jnl
Privacy-Preserving Password Cracking: How a Third Party Can Crack Our Password Hash Without Learning the Hash Value or the Cleartext.
IEEE Trans. Inf. Forensics Secur.
Norbert Tihanyi, Tamás Bisztray, Bertalan Borsos, Sebastien Raveau
2024 — conf
Rapid Taint Assisted Concolic Execution (TACE).
SIGSOFT FSE Companion
Ridhi Jain, Norbert Tihanyi, Mthandazo Ndhlovu, Mohamed Amine Ferrag, Lucas C. Cordeiro
2024 J jnl
Revolutionizing Cyber Threat Detection With Large Language Models: A Privacy-Preserving BERT-Based Lightweight Model for IoT/IIoT Devices.
IEEE Access
Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi, Lucas C. Cordeiro, Mérouane Debbah, Thierry Lestable, Narinderjit Singh Thandi
2024 J jnl
Securing Tomorrow's Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies.
CoRR
Ridhi Jain, Norbert Tihanyi, Mohamed Amine Ferrag
2023 J jnl
A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification.
CoRR
Yiannis Charalambous, Norbert Tihanyi, Ridhi Jain, Youcheng Sun, Mohamed Amine Ferrag, Lucas C. Cordeiro
2023 J jnl
ESBMC v7.4: Harnessing the Power of Intervals.
CoRR
Rafael Menezes, Mohannad Aldughaim, Bruno Farias, Xianzhiyu Li, Edoardo Manino, Fedor Shmarov, Kunjian Song, Franz Brauße, Mikhail R. Gadelha, Norbert Tihanyi, Konstantin Korovin, Lucas C. Cordeiro
2023 J jnl
Edge Learning for 6G-Enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses.
IEEE Commun. Surv. Tutorials
Mohamed Amine Ferrag, Othmane Friha, Burak Kantarci, Norbert Tihanyi, Lucas C. Cordeiro, Mérouane Debbah, Djallel Hamouda, Muna Al-Hawawreh, Kim-Kwang Raymond Choo
2023 J jnl
Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses.
CoRR
Mohamed Amine Ferrag, Othmane Friha, Burak Kantarci, Norbert Tihanyi, Lucas C. Cordeiro, Mérouane Debbah, Djallel Hamouda, Muna Al-Hawawreh, Kim-Kwang Raymond Choo
2023 J jnl
Privacy-Preserving Password Cracking: How a Third Party Can Crack Our Password Hash Without Learning the Hash Value or the Cleartext.
CoRR
Norbert Tihanyi, Tamás Bisztray, Bertalan Borsos, Sebastien Raveau
2023 J jnl
Revolutionizing Cyber Threat Detection with Large Language Models.
CoRR
Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi, Lucas C. Cordeiro, Mérouane Debbah, Thierry Lestable
2023 J jnl
SecureFalcon: The Next Cyber Reasoning System for Cyber Security.
CoRR
Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi, Mérouane Debbah, Thierry Lestable, Lucas C. Cordeiro
2023 J jnl
Simple chain automaton random number generator for IoT devices.
Acta Informatica
Pál Dömösi, Géza Horváth, Norbert Tihanyi
2023 J jnl
The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification.
CoRR
Norbert Tihanyi, Tamás Bisztray, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro, Vasileios Mavroeidis
2023 — conf
The FormAI Dataset: Generative AI in Software Security through the Lens of Formal Verification.
PROMISE
Norbert Tihanyi, Tamás Bisztray, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro, Vasileios Mavroeidis
2022 J jnl
Report on the First DES Fixed Points for Non-Weak Keys: Case-Study of Hacking an IoT Environment.
IEEE Access
Norbert Tihanyi
2021 J jnl
A Full Cycle Length Pseudorandom Number Generator Based on Compositions of Automata.
Informatica (Slovenia)
Bertalan Borsos, Pál Dömösi, Yousef AlHammadi, Norbert Tihanyi, József Gáll, Géza Horváth
2021 J jnl
A Pseudorandom number Generator with Full Cycle Length based on Automata Compositions.
Informatica (Slovenia)
Bertalan Borsos, Pál Dömösi, Yousef AlHammadi, Norbert Tihanyi, József Gáll, Géza Horváth
2021 — conf
Creating effective fingerprint artefacts: a cooperative and a non-cooperative method for bypassing capacitive and optical sensors with high success rate.
ICCST
Ryan Carvalho, Norbert Tihanyi
2020 Misc conf
A general construction for generating pseudorandom sequences using the digit expansion of real functions.
SYNASC
Norbert Tihanyi, Bertalan Borsos
2020 — —
Numerical computing of extremely large values of the Riemann-Siegel Z-function
Norbert Tihanyi
2020 — conf
The Theory and Practice of Magic Hash Based Attacks on Lightweight Cryptographic Hash Functions in Complex IoT Environments.
SpaCCS Workshops
Norbert Tihanyi, Bertalan Borsos
2019 J jnl
Some Remarks and Tests on the Dh1 Cryptosystem Based on Automata Compositions.
Informatica (Slovenia)
Pál Dömösi, József Gáll, Géza Horváth, Norbert Tihanyi
2018 Misc conf
Computation Results of the Riemann Zeta Search Project.
SYNASC
Norbert Tihanyi, Attila Kovács
2017 J jnl
Computing Extremely Large Values of the Riemann Zeta Function.
J. Grid Comput.
Norbert Tihanyi, Attila Kovács, József Kovács
2017 J jnl
Statistical Analysis of DH1 Cryptosystem.
Acta Cybern.
Pál Dömösi, József Gáll, Géza Horváth, Norbert Tihanyi
2014 Misc conf
Fast Method for Locating Peak Values of the Riemann Zeta Function on the Critical Line.
SYNASC
Norbert Tihanyi
2014 — conf
Unrevealed Patterns in Password Databases Part One: Analyses of Cleartext Passwords.
PASSWORDS
Norbert Tihanyi, Attila Kovács, Gergely Vargha, Ádám Lénárt