No abstract

Software birthmarking relies on unique characteristics that are inherent to a program to identify the program in the event of suspected theft. In this paper we present and empirically evaluate a novel birthmarking technique which uniquely identifies a program through instruction sequences. To evaluate the strength of the birthmarking technique we examine two properties: credibility and resilience to semantics-preserving transformations. We show that the technique provides both high credibility and resilience. Additionally, it complements previously proposed static birthmarking techniques.

Abstract.A software birthmark is a unique characteristic of a program that can be used as a software theft detection technique. In this paper we present and empirically evaluate a novel birthmarking technique -Whole Program Path Birthmarking -which uniquely identifies a program based on a complete control flow trace of its execution. To evaluate the strength of the proposed technique we examine two important properties: credibility and tolerance against program transformations such as optimization and obfuscation. Our evaluation demonstrates that, for the detection of theft of an entire program, Whole Program Path birthmarks are more resilient to attack than previously proposed techniques. In addition, we illustrate several instances where a birthmark can be used to identify program theft even when an embedded watermark was destroyed by program transformation.

No abstract

Within the software industry software piracy is a great concern. In this article we address this issue through a prevention technique called software watermarking. Depending on how a software watermark is applied it can be used to discourage piracy; as proof of authorship or purchase; or to track the source of the illegal redistribution. In particular we analyze an algorithm originally proposed by Geneviève Arboit in A Method for Watermarking Java Programs via Opaque Predicates. This watermarking technique embeds the watermark by adding opaque predicates to the application. We have found that the Arboit technique does withstand some forms of attack and has a respectable data-rate. However, it is susceptible to a variety of distortive attacks. One unanswered question in the area of software watermarking is whether dynamic algorithms are inherently more resilient to attacks than static algorithms. We have implemented and empirically evaluated both static and dynamic versions within the SANDMARK framework.