Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs
cs.CL, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Linear socio-demographic representations emerge in Large Language Models from indirect cues
- When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data