Generating Realistic Fake Equations in Order to Reduce Intellectual Property Theft
Yanhai Xiong, Giridhar Kaushik Ramachandran, Rajesh Ganesan, Sushil Jajodia, V. S. Subrahmanian · IEEE Transactions on Dependable and Secure Computing · 2020
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${\sf FEE}$(Fake Equation Engine), a framework to generate fake equations in such documents.${\sf FEE}$tries to preserve multiple aspects of a given equation when generating a fake. Moreover,${\sf FEE}$is very general and applies to diverse equational forms including polynomial equations, differential equations, transcendental equations, and more.${\sf FEE}$iteratively solves a complex, changing optimization problem inside it. We also present${\sf FEE-FAST}$, a fast approximate algorithm to solve the optimization problem within${\sf FEE}$. Using a panel of human subjects, we show that${\sf FEE}$achieves a high rate in deceiving sophisticated subjects.