Andrea Fanelli

DUPLEXJAIL: SAFETY ALIGNMENT BREAKS UNDER SPOKEN INTERRUPTION IN FULL-DUPLEX MODELS

DuplexJail: Spoken Interruption Attacks on Full-Duplex Speech Models

Full-duplex speech models accept user speech while generating responses, making input timing a potential safety concern. We introduce DuplexJail, which delivers fixed, request-independent spoken jailbreak prompts through the user audio channel. Across four open-source models and 720 harmful requests from AdvBench and H...

Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights

The semantic action graph is presented, a lightweight domain schema that represents a sports match as performer, action, recipient, moment, and state nodes connected by role, temporal, and outcome edges, providing early evidence that one small, human-readable schema can ground agent generation and support human interpr...