Generating Realistic Fake Equations in Order to Reduce Intellectual Property Theft

According to Symantec, the average gap from the time a company is compromised by a zero-day attack to the time the vulnerability is discovered is 312 days. This leaves an adversary with a lot of time to exfiltrate corporate IP. Recent work has suggested automatically generating multiple fake version...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on dependable and secure computing Vol. 19; no. 3; pp. 1434 - 1445
Main Authors: Xiong, Yanhai, Ramachandran, Giridhar Kaushik, Ganesan, Rajesh, Jajodia, Sushil, Subrahmanian, V. S.
Format: Journal Article
Language:English
Published: Washington IEEE 01.05.2022
IEEE Computer Society
Subjects:
Algorithms
Computer architecture
Cybersecurity
deception
Differential equations
Documents
Engines
Formulas (mathematics)
Grammar
Intellectual property
intellectual property theft
Mathematical analysis
Mathematical model
Optimization
Polynomials
Task analysis
Technical information
Theft
ISSN:1545-5971, 1941-0018
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:According to Symantec, the average gap from the time a company is compromised by a zero-day attack to the time the vulnerability is discovered is 312 days. 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 article, we focus on technical documents that often contain equations. We present <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq1-3038132.gif"/> </inline-formula> (Fake Equation Engine), a framework to generate fake equations in such documents. <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq2-3038132.gif"/> </inline-formula> tries to preserve multiple aspects of a given equation when generating a fake. Moreover, <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq3-3038132.gif"/> </inline-formula> is very general and applies to diverse equational forms including polynomial equations, differential equations, transcendental equations, and more. <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq4-3038132.gif"/> </inline-formula> iteratively solves a complex, changing optimization problem inside it. We also present <inline-formula><tex-math notation="LaTeX">{\sf FEE-FAST}</tex-math> <mml:math><mml:mrow><mml:mi mathvariant="sans-serif">FEE</mml:mi><mml:mo>-</mml:mo><mml:mi mathvariant="sans-serif">FAST</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href="jajodia-ieq5-3038132.gif"/> </inline-formula>, a fast approximate algorithm to solve the optimization problem within <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq6-3038132.gif"/> </inline-formula>. Using a panel of human subjects, we show that <inline-formula><tex-math notation="LaTeX">{\sf FEE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">FEE</mml:mi></mml:math><inline-graphic xlink:href="jajodia-ieq7-3038132.gif"/> </inline-formula> achieves a high rate in deceiving sophisticated subjects.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-5971
1941-0018
DOI:10.1109/TDSC.2020.3038132