Aylin Yener

Downstream classifier accuracy can actually improve when neural compressors intentionally distort reconstruction distributions away from mismatched source domains toward a target distribution.

Relay nodes can reconstruct semantic information with surprising accuracy, exposing a critical privacy flaw in current SemCom systems.

A stealthy low-power backdoor attack can selectively manipulate semantic inference in shared-access wireless networks, exposing significant vulnerabilities in current SemCom systems.