4 papers
On the security and privacy of LLMs in Mobility
Mauro Conti, Lorenzo Perinello, Umberto Salviati
The mobility sector is undergoing a paradigm shift driven by advances in Generative Artificial Intelligence. With a global market valued at approximately 2.9 trillion dollars annua…
ShellGames: Speculative LLM-Driven SSH Deception
Umberto Salviati, Fabio De Gaspari, Mauro Conti +1
Cyber deception and Moving Target Defense are promising strategies that aim to disrupt adversaries by increasing uncertainty. However, sustaining long-lived, credible interactive s…
Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
Matteo Gioele Collu, Umberto Salviati, Roberto Confalonieri +2
Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation…
The Hidden Threat in Plain Text: Attacking RAG Data Loaders
Alberto Castagnaro, Umberto Salviati, Mauro Conti +2
Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhan…