collaborators

14 papers

cs.CR2026

An AI-Based Solution for Secure Service Provisioning in IoT

Marco Arazzi, Mert Cihangiroglu, Serena Nicolazzo +2

As the Internet of Things (IoT) continues its rapid expansion, the attack surface grows accordingly, with emerging threats targeting smart objects and their interactions. In this e…

cs.CR2026

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation

Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera +2

The open-source ecosystem has accelerated the democratization of Large Language Models (LLMs) through the public distribution of specialized Low-Rank Adaptation (LoRA) modules. How…

cs.CR2026

Security in LLM-as-a-Judge: A Comprehensive SoK

Aiman Al Masoud, Antony Anju, Marco Arazzi +6

LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has sig…

cs.CR2026

SecureBreak -- A dataset towards safe and secure models

Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe…

cs.IR2026

Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards

Aiman Al Masoud, Marco Arazzi, Simone Germani +1

Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it chal…

cs.CR2026

LoRA as Oracle

Marco Arazzi, Antonino Nocera

Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical settings. Existing defenses for backdoo…