AI Squawk the real-time terminal for AI news

↗

RESEARCH Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs

We propose Synthesis Smuggling, a novel threat model in which an adversarial LLM infers sensitive information about a user from routine…

Source tier 2: +25
Category RESEARCH: +10
Other adjustment (same-source burst decay, or scored under an earlier weighting): −10
Base score: 25
Velocity (0 corroborating sources): +0
Age decay (44h since published): −25
Effective score right now: 0