基于即时编译的动态污点跟踪优化  

Dynamic Taint Tracking Optimization on Just-in-Time Compilation

作　　者：吴泽智[1,2] 陈性元[1,2] 杨智[1,3] 杜学绘[1,3] 

机构地区：[1]解放军信息工程大学三院,河南郑州450001 [2]密码科学技术国家重点实验室(北京信息科学技术研究院),北京100094 [3]河南省信息安全重点实验室(解放军信息工程大学),河南郑州450001

出　　处：《软件学报》2017年第8期2064-2079,共16页Journal of Software

基　　金：国家自然科学基金(61402437);国家高技术研究发展计划(863)(2015AA016006;2012AA012704)~~

摘　　要：动态污点跟踪技术展现了在移动隐私保护方面的强大功能,但存在系统性能较低问题.提出了一种基于即时编译的动态污点传播优化方法.首先,将程序逻辑精确抽象为污点传播逻辑,简化污点传播分析复杂性;然后,提出了一个污点传播框架,并证明了在该框架下污点传播分析的正确性和有效性;最后,采用消除、替换和移动等方法将冗余低效的污点传播代码转化为高效等价的污点传播代码.实验结果表明,经过优化后,单条热路径的污点传播代码节省了38%的内存占用和指令执行时间,系统整体性能平均提升了6.8%.Despite the demonstrated usefulness of dynamic taint tracking techniques in mobile privacy security, poor performance attained by prototypes is a big problem. A novel optimization methodology for dynamic taint tracking based on just-in-time compilation is presented. First, the taint propagation logic is separated from the program logic precisely to simplifying the complexity of the taint propagation analysis. Then, a taint propagation framework is proposed and the correctness of the taint propagation analysis is proved..Finally, redundant and inefficient taint propagation codes are transferred to efficient and equivalent codes by adopting the methods of eliminating, replacing and moving. Experimental results show that 38% of memory usage and the time of execution of taint tracking instructions are saved for every single hot trace, and on average the performance of dynamic taint tracking system is improved 6.8%.

关 键 词：安卓 隐私安全 动态污点跟踪 即时编译器 污点传播优化 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]