Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911990117564416 |
|---|---|
| author | Bauer, Luke A. Howes IV, James K. Markelon, Sam A. Bindschaedler, Vincent Shrimpton, Thomas |
| author_facet | Bauer, Luke A. Howes IV, James K. Markelon, Sam A. Bindschaedler, Vincent Shrimpton, Thomas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2110_07009 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments Bauer, Luke A. Howes IV, James K. Markelon, Sam A. Bindschaedler, Vincent Shrimpton, Thomas Cryptography and Security Machine Learning 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. |
| title | Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2110.07009 |