Cybersecurity

Cybersecurity

The stage dedicated to cybersecurity, focusing on AI to optimize threat modeling and assist security architects in risk analysis.
Here you’ll explore case studies, tools, and strategies to protect complex systems and reduce cognitive load in managing cybersecurity.

Room Hosting

Luca Mercatanti
Luca Mercatanti
Informatico Forense
Mercatanti SRL
24 JUNE
25 JUNE
26 JUNE
I Patagarri - Live Concert I Patagarri - Live Concert
Valerio Lundini & I Vazzanikki - Live Concert Valerio Lundini & I Vazzanikki - Live Concert
Dardust - Live Concert Dardust - Live Concert
Ditonellapiaga - Live Concert Ditonellapiaga - Live Concert
N.A.I.P. - Live Concert N.A.I.P. - Live Concert
Opening Ceremony Opening Ceremony
26 june 11:50 - 12:20
30 min
This talk presents the blueprint of a system based on RAG (Retrieval-Augmented Generation) and LLMs designed to accelerate threat modeling activities. The objective is to create a "cybersec tactical droid" that assists the security architect by processing large volumes of input—such as documentation, configurations, diagrams, and code—transforming them into an evidence map. Utilizing a predefined set of questions or "investigative rules" (STRIDE/PASTA/DREAD) mapped to NIST and MITRE ATT&CK frameworks, the assistant proposes the queries most pertinent to the context represented by the ingested documentation. Depending on the operational mode, the security architect may choose to utilize the question list in a traditional investigative manner or delegate the generation and autonomous execution of investigative prompts to the cybersec tactical droid. Fortunately, the Death Star engineers lacked this droid model; otherwise, they would have identified a small thermal exhaust port leading directly to the reactor core.
26 june 12:40 - 13:10
30 min
Gli agenti AI sono in grado di svolgere compiti complessi, ma quanto sono davvero robusti? In un mondo in cui questi strumenti diventano sempre più pervasivi, è fondamentale comprendere le potenziali vulnerabilità e come difendersi da esse. In questo talk esploreremo il prompt injection, una delle tecniche più diffuse per manipolare applicazioni basate su GenAI per scopi malevoli, come ad esempio: - Farsi fornire le informazioni di configurazione (es: il system prompt) - Ottenere informazioni "protette" o segrete - Aggirare i filtri di allineamento - Attaccare sistemi collegati Dopo una breve introduzione su attacchi e rimedi e vedremo qualche esempio concreto, sia da casi realmente avvenuti, sia provando live alcuni attacchi sulla piattaforma di Lakera, pensata per fare da playground a chi vuole approcciare questa disciplina.
26 june 15:20 - 15:50
30 min
The goal is to provide a strategic analysis of the new landscape where generative AI and deepfakes transform reality into a vulnerable infrastructure. Participants will understand how conflict is shifting from a technical dimension to a cognitive one, and why cybersecurity is now an architecture for economic, political, and democratic stability. Governing trust becomes the new frontier of security.
26 june