StegoNet: Turn Deep Neural Network into a Stegomalware

Tao Liu, Zihao Liu, Qi Liu, Wujie Wen, Wenyao Xu, Ming Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Deep Neural Networks (DNNs) are now presenting human-level performance on many real-world applications, and DNN-based intelligent services are becoming more and more popular across all aspects of our lives. Unfortunately, the ever-increasing DNN service implies a dangerous feature which has not yet been well studied-allowing the marriage of existing malware and DNN model for any pre-defined malicious purpose. In this paper, we comprehensively investigate how to turn DNN into a new breed evasive self-contained stegomalware, namely StegoNet, using model parameter as a novel payload injection channel, with no service quality degradation (i.e. accuracy) and the triggering event connected to the physical world by specified DNN inputs. A series of payload injection techniques which take advantage of a variety of unique neural network natures like complex structure, high error resilience capability and huge parameter size, are developed for both uncompressed models (with model redundancy) and deeply compressed models tailored for resource-limited devices (no model redundancy), including LSB substitution, resilience training, value mapping, and sign-mapping. We also proposed a set of triggering techniques like logits trigger, rank trigger and fine-tuned rank trigger to trigger StegoNet by specific physical events under realistic environment variations. We implement the StegoNet prototype on Nvidia Jetson TX2 testbed. Extensive experimental results and discussions on the evasiveness, integrity of proposed payload injection techniques, and the reliability and sensitivity of the triggering techniques, well demonstrate the feasibility and practicality of StegoNet.

Original languageEnglish (US)
Title of host publicationProceedings - 36th Annual Computer Security Applications Conference, ACSAC 2020
PublisherAssociation for Computing Machinery
Pages928-938
Number of pages11
ISBN (Electronic)9781450388580
DOIs
StatePublished - Dec 7 2020
Externally publishedYes
Event36th Annual Computer Security Applications Conference, ACSAC 2020 - Virtual, Online, United States
Duration: Dec 7 2020Dec 11 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference36th Annual Computer Security Applications Conference, ACSAC 2020
Country/TerritoryUnited States
CityVirtual, Online
Period12/7/2012/11/20

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'StegoNet: Turn Deep Neural Network into a Stegomalware'. Together they form a unique fingerprint.

Cite this