cs.CLNov 12, 2026

Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs

Authors: Gautam Galada, Supreeth Shastri, Sagnik Ray Choudhury

Organizations: University of North Texas

Abstract

We propose Synthesis Smuggling, a novel threat model in which an adversarial LLM infers sensitive information about a user from routine assistance-seeking interactions and steganographically encodes that into innocuous-looking model-generated content. The user may then unknowingly transmit that information by sharing the generated artifact, say as an email, social-media post, or message, through ordinary communication channels. An adversary monitoring these channels can discover this information. We demonstrate this threat by training two open-weight models to infer gender and age-group labels from conversational cues and encode their predictions using invisible characters or word choices. These results show that user-shared model outputs can become a covert channel for personal inferences, even when the model itself has no direct means of contacting an adversary.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants

    Oct 25, 2026Pengrun Huang, Yiwei Fu, Luoxi Meng +1Privacy Leakage in Language ModelsPrivacy Protection for LLM Agents

  2. Inadvertent Context Leakage in Language Models

    Aug 20, 2026Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri +2Privacy Leakage in Language ModelsLLM Security

  3. GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs

    Sep 11, 2026Ahmed Sohair Khan, Estrid He, Chenglong Ma +2Privacy AuditingPrivacy Leakage in Language Models