Dynamic data flow tracking (DFT) deals with tagging and tracking data of interest as they propagate during program execution. DFT has been repeatedly implemented by a variety of tools for numerous purposes, including protection from zero-day and cross-site scripting attacks, detection and prevention of information leaks, and for the analysis of legitimate and malicious software. We present libdft, a dynamic DFT framework that unlike previous work is at once fast, reusable, and works with commodity software and hardware. libdft provides an API for building DFT-enabled tools that work on unmodified binaries, running on common operating systems and hardware, thus facilitating research and rapid prototyping. We explore different approaches for implementing the low-level aspects of instruction-level data tracking, introduce a more efficient and 64-bit capable shadow memory, and identify (and avoid) the common pitfalls responsible for the excessive performance overhead of previous studies. We evaluate libdft using real applications with large codebases like the Apache and MySQL servers, and the Firefox web browser. We also use a series of benchmarks and utilities to compare libdft with similar systems. Our results indicate that it performs at least as fast, if not faster, than previous solutions, and to the best of our knowledge, we are the first to evaluate the performance overhead of a fast dynamic DFT implementation in such depth. Finally, libdft is freely available as open source software.

Offloading complex tasks to a resource-abundant environment like the cloud, can extend the capabilities of resource constrained mobile devices, extend battery life, and improve user experience. Split browsing is a new paradigm that adopts this strategy to improve web browsing on devices like smartphones and tablets. Split browsers offload computation to the cloud by design; they are composed by two parts, one runningon the thin client and one in the cloud. Rendering takes place primarily in the latter, while a bitmap or a simplified web page is communicated to the client. Despite its difference with traditional web browsing, split browsing still suffers from the same types of threats, such as cross-site scripting. In this paper, we propose exploiting the design of split browsers to also utilize cloud resources for protecting against various threats efficiently. We begin by systematically studyingsplitbrowsingarchitectures, andthenproceed to propose two solutions, in parallel and inline cloning, that exploit the inherent features of this new browsing paradigm to accurately and efficiently protect user data against common web exploits. Our preliminary results suggest that our framework can be efficiently applied to Amazon’s Silk, the most widely deployed at the time of writing, split browser.