Friday, September 18, 2026
Room P1, Building CU037
| Time | Session |
|---|---|
| 09:00–09:15 | Welcome and Opening Remarks |
| 09:15–09:35 | Make the Adversary Spend More: Stateful Deception as a Cost-Exchange Primitive for AI-Era Cyber Defense – Alessandro Cantelli-Forti, Isabella Marasco, Hosam Alamleh, Giada Boschi, Michele Colajanni |
| 09:35–09:55 | Honey for the Agent: Cyber Deception and Behavioral Fingerprinting of LLM-Based Attackers – Dario Maddaloni, Anastasia Safargalieva, Emmanouil Vasilomanolakis |
| 09:55–10:15 | AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deception – Muris Sladić, Eman Alibalić, Veronica Valeros, Carlos Catania, Sebastian Garcia |
| 10:15–10:30 | Position Paper: Bridging Cyber Deception and CTI through STIX-Based Honeypot Log Mapping – Karina Elzer, Tillmann Angeli, Stylianos Malamas, Emmanouil Vasilomanolakis |
| 10:30–10:50 | Coffee Break |
Room P1, Building CU037
| Time | Session |
|---|---|
| 10:50–11:10 | HoneyPeople: When Decoys Talk Back – Claudio Facchinetti, Daniele Santoro, Roberto Doriguzzi Corin, Domenico Siracusa |
| 11:10–11:30 | No Time for Harvesting: Deception-Assisted Attribution of IPv6 Address Leakage in the NTP Pool – Stefan Groser, Sajad Homayoun |
| 11:30–11:50 | Decoys Cannot Go Everywhere: Mapping the Deception Surface in MITRE ATT&CK – Veronica Valeros, Carlos Catania, Viliam Lisý, Harm Griffioen |
| 11:50–12:05 | Position Paper: Development of an Automated Vulnerability Placement Framework for IaC-Based Honeynets – Marvin Sinnwell, Daniel Reti, Hans D. Schotten |
| 12:05–12:20 | Closing remarks and Open Discussion |
| 12:20–13:50 | Lunch |
Room 201, Building CU002
| Time | Session |
|---|---|
| 13:50–14:40 | Keynote: Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks - Giovanni Appruzzese |
| Abstract: Large Language Models (LLMs) have revolutionized many aspects of our society. Many tasks encompassing document summarization or autonomous content generation can now benefit from the capabilities of LLMs. Among these, a domain in which LLMs are receiving incresing attention is that of scientific peer reviewing. Yet, usage of LLMs in this context must be done with due care: LLMs have certain blind spots which, if exploited, can lead to detrimental effects to the human requesting the service of an LLM. In this talk, I will outline the reasons why the author of a scientific paper may want to mislead an LLM tasked to review a given paper. Based on these reasons, I will then explain ways in which one can reach their goal via “hidden prompt injections”. Finally, I will discuss the results of a large-scale systematic analysis wherein we studied the impact of prompt-injection attacks against commercial LLMs (e.g., ChatGPT, Gemini). In doing so, I will also outline potential countermeasures—as well as counter-countermeasures. The takeaway is that blind reliance on LLMs for peer-review duties is strongly discouraged, and human oversight is still necessary. | |
| Bio: Giovanni Apruzzese is an Assistant Professor within the Department of Computer Science at Reykjavik University, Iceland. Prior to this, he was affiliated with the Hilti Chair of Data and Application Security at the University of Liechtenstein—first as a PostDoc and then as an Assistant Professor. He obtained the PhD in Information and Communication Technologies at the University of Modena and Reggio Emilia (Italy) in 2020. He authored over 50 peer-reviewed papers at internationally-recognized research venues. His research interests encompass a variety of themes, most of which revolve around cybersecurity and artificial intelligence, but he also appreciates topics within human-computer interaction. His primary expertise lies in network security and in phishing detection. Giovanni also puts a lot of effort in servicing the scientific community, and he was awarded numerous recognitions for his reviewing duties in leading computer-science venues. He is the General Chair of IEEE SaTML 2027, one of the PC Co-chairs of ACM AISec 2026, one of the PC Vice-chairs of USENIX Security 2026, and has been an Associate Editor for ACM TAISAP since 2025, and an Area Chair for NeurIPS since 2024. Due to his interest in reviewing and his servicing committments, he has also recently engaged in researching the usage of large-language models for scientific peer reviewing. | |
| Keynote in collaboration with HumSec, RAISE, and HotDiSec. |