Generating Realistic Fake Equations in Order to Reduce Intellectual Property Theft

Yanhai Xiong, Giridhar Kaushik Ramachandran, Rajesh Ganesan, Sushil Jajodia, V. S. Subrahmanian

Research output: Contribution to journalArticlepeer-review

Abstract

According to research from Symantec, there is a gap of 312 days on average between the time an enterprise is compromised by a zero-day attack and the time the attack is discovered by the victim. This leaves an adversary with a lot of time to exfiltrate corporate IP. Recent work has suggested automatically generating multiple fake versions of a document to impose costs on the attacker who needs to correctly identify the original document from a set of mostly fake documents. But in the real world, documents contain many diverse components. In this paper, we focus on technical documents that often contain equations and present FEE, a framework to generate fake equations in such documents. FEE tries to preserve multiple aspects of a given equation when generating a fake. Moreover, FEE is very general and applies to diverse equational forms including polynomial equations, differential equations, transcendental equations, and more. FEE iteratively solves a complex, changing optimization problem inside it. We also present FEE-FAST, a fast approximate algorithm to solve the optimization problem within FEE. Using a panel of human subjects, we show that FEE achieves a high rate in deceiving sophisticated subjects.

Original languageEnglish (US)
JournalIEEE Transactions on Dependable and Secure Computing
DOIs
StateAccepted/In press - 2020
Externally publishedYes

Keywords

  • Computer architecture
  • cybersecurity
  • deception
  • Engines
  • Grammar
  • Intellectual property
  • intellectual property theft
  • Mathematical model
  • Optimization
  • Task analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Generating Realistic Fake Equations in Order to Reduce Intellectual Property Theft'. Together they form a unique fingerprint.

Cite this