GAIT: A Game-Theoretic Defense Against Intellectual Property Theft
Youzhi Zhang, Dongkai Chen, Sushil Jajodia, Andrea Pugliese, V. S. Subrahmanian, Yanhai Xiong · IEEE Transactions on Dependable and Secure Computing · 2023
Months may pass before the victim of IP theft even knows they have been compromised. During this time, the attacker can exfiltrate large amounts of data. Recent work has proposed the idea of injecting a set of believable fake versions of a real document into a network so that the attacker has to expend time and effort to identify the real document from a sea of similar documents. In this paper, we consider the problem of an attacker who is smart and breaks a technical document down into small, bit-sized “units” and inspects them one by one so as to defeat the fake document defense. If a unit in a document is determined to be fake, the adversary does not need to look further at the same document. He can also immediately identify as fake, any other document that contains the same unit. In this paper, we consider the problem of a smart attacker using this strategy. Our proposed defensive algorithm, called${\sf GAIT}$, is shown to be successful in mitigating such attacks.${\sf GAIT}$can work in conjunction with any NLP-based generative method to create fake technical documents.