Program Schedule
14:30 - 14:45
Introduction
15 minutes
ACTE - Opening Session
14:45 - 15:15
Keynote
30 minutes (25 min talk + 5 min Q&A)
On-device derivation of IoT usage control policies: Automating U-XACML policy generation from natural language with LLMs in smart homes environments
Andrea Saracino
In this paper, we present a framework that integrates AI-based derivation of Access and Usage Control policies for IoT devices, using Large Language Models (LLMs) to automate the generation of policies from unstructured natural language commands...
The framework employs a hybrid approach, combining LLMs with dedicated libraries to ensure efficient on-device execution. Our approach is based on a two-step process: first, a fine-tuned LLM converts user commands into structured JSON policy representations; then, a transformation module translates the JSON policies into fully compliant U-XACML policies. To ensure generality across different domains, we introduce a taxonomy-driven dataset creation, which enables policy creation for different environments such as smart homes, smart offices, and healthcare settings. Our evaluation demonstrates that the system achieves 93% accuracy in policy generation and 91% accuracy when handling ambiguous or noisy inputs. It also reaches 98% agreement with expert-defined policies in real-world scenarios. Finally, on-device performance evaluations confirm the feasibility of running the model in practical settings, demonstrating reliable inference under constrained hardware conditions.
15:15 - 15:30
Speaker
15 minutes (10 min talk + 5 min Q&A)
Leveraging LLMs for Cyber Threat Intelligence: Opportunities and Challenges
Nicola Deidda
15:30 - 16:00
Speaker
15 minutes (10 min talk + 5 min Q&A)
It's all about the journey and not the destination: Placing cybersecure generative AI models on the Market
Margaret Varilek & Federica Casarosa
16:00 - 16:30
Coffee Break
30 minutes
Networking & Refreshments
16:30 - 17:00
Keynote
30 minutes (25 min talk + 5 min Q&A)
Criminal Misuse of Generative AI: Legal Constraints, Risks, and Responsibilities
Gaia Fiorinelli
The speech explores the criminal misuse of Generative AI (GenAI), emphasizing how its democratization has facilitated exploitation by cybercriminals...
It discusses the risks associated with GenAI and highlights the need for new legal frameworks to address these (cyber) threats. The speech also touches on the responsibility of AI developers for self-regulation and advocates for a balanced approach that integrates criminal law, AI regulation, and cybersecurity measures to mitigate misuse while fostering innovation.
17:00 - 17:15
Speaker
15 minutes (10 min talk + 5 min Q&A)
Ethical, Legal, and Societal Risks of Generative AI in Medicine — Lessons from Ophthalmology
Dennis Glenn Ejeh
17:15 - 17:30
Closing
15 minutes