Galli, D., Artioli, A., Andreolini, M., Stabili, D., Apruzzese, G., Marchetti, M., European Symposium on Research In Computer Security, 2026 Conference Oneliner: We propose an evaluation framework for measuring the performance of LLMs in se…
Apruzzese, G., ACM Asia Conference on Computer and Communications Security, 2026 Conference Oneliner: We endorse future work in this space to follow the three assertions stated here. Abstract. Network Intrusion Detection Systems (NIDS) have…
Verkerken, M., D'hooge, L., Volckaert, B., De Turck, Filip, & Apruzzese, G., ACM Asia Conference on Computer and Communications Security, 2026 Conference Oneliner: Changing one character of one command can lead to a complete bypass. Abstrac…
Ave, J., Pekaric, I., Frohner, M., Apruzzese, G., European Symposium on Research In Computer Security, 2026 Conference Oneliner: To fight toxicity, we manually labeled an (open-source) dataset of toxic LoL matches, and show its utility for
Collu, M. G., Salviati, U., Confalonieri, R., Conti., M., Apruzzese, G. , ACM Transactions on AI Security and Privacy, 2026 Journal Oneliner: We systematically analyse how, and why, LLMs can be misled in a peer-review context. Abstract. Lar…
Yuan, Y., Rado, C. A., Apruzzese, G., Conti, M., & Mancini, L. V., IEEE European Symposium on Security and Privacy, 2026 Conference Oneliner: We identify and systematically analyse a fundamental weakness of visual phishing detectors. Abstra…
Moosmann, J., Pekaric, I., Apruzzese, G., Conference on Detection of Intrusions and Malware & Vulnerability Assessment, 2026 Conference Oneliner: Apparently, the operators of our examined SOC mostly rely on 'gut feelings'. Abstract. Securit…
Rizvani, A., Apruzzese, G., Laskov, P., IEEE Conference on Secure and Trustworthy Machine Learning, 2025 Conference Oneliner: Abstract. Large Language Models (LLMs) are increasingly adopted in the financial domain. Their exceptional capabil…
Verkerken, M., D'hooge, L., Volckaert, B., De Turck, F., Apruzzese, G., IEEE Conference on Secure and Trustworthy Machine Learning, 2025 Conference Oneliner: We propose a full-fledged system to create fine-grained labeled NetFlows. ML-drive…
Seminar Dagstuhl Seminars: Security and Privacy of Large Language Models November 10, 2025 Dagstuhl, Germany Oneliner: The best thing about phishing, research-wise, is that everyone can relate to it. Abstract: Every day, our inboxes are flo…
Rosenzweig, B., Dalla Valle, V., Apruzzese, G., Fass, A., ACM Transactions on the Web [ORAL @ TheWebConf'26], 2025 Journal Oneliner: Nobody really _tried_ to use supervised ML to detect browser extensions. So, we tried. Results were... Abst…
Schröer, S. L., Pajola, L., Castagnaro, A., Apruzzese, G., & Conti, M., IEEE Intelligent Systems, 2025 Journal Oneliner: There are far too many terms associated to "AI." We examine and clarify them a bit. Abstract. As Artificial Intelligenc…