Hello, and welcome! I’m an incoming tenure-track Assistant Professor of Information Systems and Security
at Kennesaw State University’s
Coles College of Business.
I completed my Ph.D. in Information Technology at UT San Antonio, where I worked with
Dr. Anthony Rios. Broadly, my work sits at the intersection of cybersecurity, trustworthy AI,
and responsible language technologies.
Research
I build trustworthy AI systems for high-stakes settings where models must reason about
privacy, access, fairness, and security. My work asks when AI systems should
answer, refuse, reveal, or protect.
Confidentiality & Authorization in LLMs
How can language models respect roles, permissions, and private data?
Role-Conditioned Refusals
Latent Refusal Probing for Access Control
Text-to-SQL Database Vulnerability Analysis
Equal Access & Protection
How can language technologies provide the same quality, privacy, and protection across dialects and writing styles?
Multi-Agent Dialect-Bias Mitigation
Prompt-Probe-Gated Decoding
FairPrivacy
AI-Driven Cybersecurity
How can machine learning detect cyber threats from raw security and network data?
Jbeil: Lateral Movement Detection
IoT Malware Attribution
Helium IoT Threat Analysis
Natural Language ProcessingTrustworthy AICyber Security
Selected Publications
Author name in bold. Full list available in my CV.
Journal Articles
S. Torabi, Đorđe Klisura, J. Khoury, E. Bou-Harb, C. Assi, and M. Debbabi.
“Internet-Wide Analysis, Characterization, and Family Attribution of IoT Malware: A Comprehensive Longitudinal Study.”
IEEE Transactions on Dependable and Secure Computing (2024).
Conference Papers
Đorđe Klisura, J. Khoury, A. Kundu, R. Krishnan, and A. Rios.
“Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models.”
Findings of the ACL: EACL 2026, Mar. 2026.
Đorđe Klisura, A. Bernaga, A. K. Gárate, R. Roshan, K. Yang, H. Pataci, and A. Rios.
“A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems.”
Proceedings of the 63rd Annual Meeting of the ACL (Vol. 1: Long Papers), 2025.
Đorđe Klisura and A. Rios.
“Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems.”
Findings of the ACL: NAACL 2025, Apr. 2025, pp. 6954–6976. ISBN 979-8-89176-195-7.
J. Khoury, Đorđe Klisura, H. Zanddizari, G. D. L. T. Parra, P. Najafirad, and E. Bou-Harb.
“Jbeil: Temporal Graph-Based Inductive Learning to Infer Lateral Movement in Evolving Enterprise Networks.”
2024 IEEE Symposium on Security and Privacy (S&P), 2024, pp. 3644–3660.
Awards & Honors
Outstanding Graduate Teaching Award | College of AI, Cyber and Computing
Named the top graduate instructor at UT San Antonio CAICC.
Apr 2026
Ph.D. Student of The Year | UT San Antonio Alvarez College of Business
Awarded to the top doctoral student across all Ph.D. programs.
Jul 2025
Ph.D. Student of The Year | Information Systems & Cybersecurity Dept.
Awarded to the top doctoral student in the ISC Department.
Jul 2025
Teaching
CYBR 4330: Incident Response and Contingency Planning
Fall 2026
Kennesaw State University
IS 7330: Disaster Recovery & Business Continuity Planning
Fall 2026
Kennesaw State University
IS 2053: Programming I
Spring & Fall 2025
Primary Instructor at UT San Antonio
Overall Instructor Rating: 4.66 / 5.0
Research Presentations
Texas NLP Symposium 2026Poster Presentation · College Station, TX
Apr 2, 2026
Fall Workshop on Cybersecurity and AIPoster Presentation · San Angelo, TX
Oct 7–8, 2025
ACL 2025Poster Presentation · Vienna, Austria
Jul 27 – Aug 1, 2025
NAACL 2025Poster Presentation · Albuquerque, NM
Apr 29 – May 3, 2025
Contact
Let’s connect
I’m always glad to hear from prospective students, collaborators, and colleagues.