Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments

TL;DR

This paper examines the use of generative models for covert 'dead-drop' messaging on social media, highlighting algorithmic challenges, security tradeoffs, and providing an empirical performance analysis.

Contribution

It concretely identifies challenges and tradeoffs in deploying generative models for covert messaging, and presents an implemented system with empirical evaluation.

Findings

Identified key security and performance tradeoffs.

Developed a system for model-based covert messaging.

Provided empirical analysis of system performance and security.

Abstract

State of the art generative models of human-produced content are the focus of many recent papers that explore their use for steganographic communication. In particular, generative models of natural language text. Loosely, these works (invertibly) encode message-carrying bits into a sequence of samples from the model, ultimately yielding a plausible natural language covertext. By focusing on this narrow steganographic piece, prior work has largely ignored the significant algorithmic challenges, and performance-security tradeoffs, that arise when one actually tries to build a messaging pipeline around it. We make these challenges concrete, by considering the natural application of such a pipeline: namely, "dead-drop" covert messaging over large, public internet platforms (e.g. social media sites). We explicate the challenges and describe approaches to overcome them, surfacing in the process important performance and security tradeoffs that must be carefully tuned. We implement a system around this model-based format-transforming encryption pipeline, and give an empirical analysis of its performance and (heuristic) security.