AI safety researcher

Mauro Conti

University of Padua

Google Scholar dblp ORCID Homepage

Last 12 months5 papers

AI safety papers from the last year

On this site: 62 papers

September 2026

On the security and privacy of LLMs in Mobility
Sep 22arXiv ↗

June 2026

ShellGames: Speculative LLM-Driven SSH Deception
Jun 16arXiv ↗

May 2026

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
May 27arXiv ↗
From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
May 6arXiv ↗

April 2026

I can't recognize (yet): Delayed Rendering to Defeat Visual Phishing Detectors
Apr 30arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.