首页> 外文期刊>Journal of Real-Time Image Processing >Code obfuscation using very long identifiers for FFT motion estimation models in embedded processors
【24h】

Code obfuscation using very long identifiers for FFT motion estimation models in embedded processors

机译:对于嵌入式处理器中的FFT运动估计模型,使用非常长的标识符进行代码混淆

获取原文
获取原文并翻译 | 示例

摘要

Motion estimation is extensively used in multimedia tasks, video coding standards and home consumer devices, appearing in many FFT-based motion algorithms. On other hand, the intellectual properties of embedded microprocessor systems are typically delivered on HDL and C source code levels. Obfuscating the code is most often the only way to protect and avoid reverse engineering. This paper presents an evaluation of operations widely used in motion estimation for an embedded microprocessor for protection purposes. A set of open source obfuscation tools has been developed that allows the use of very long and hard-to-read identifiers. The implementation of comment methods also allows for the addition of copyright and limited warranty information. The obfuscated code with identifiers of up to 2,048 characters in length is tested for Altera's and Xilinx's field programmable gate arrays for a typical HDL example. Compiler penalties as well as FFT runtime results are reported.
机译:运动估计已广泛用于多媒体任务,视频编码标准和家庭消费类设备中,并出现在许多基于FFT的运动算法中。另一方面,嵌入式微处理器系统的知识产权通常在HDL和C源代码级别上交付。混淆代码通常是保护和避免反向工程的唯一方法。本文提出了一种用于保护目的的嵌入式微处理器运动评估中广泛使用的操作的评估。已经开发了一套开放源代码混淆工具,允许使用非常长且难以读取的标识符。评论方法的实施还允许添加版权和有限的保修信息。对于典型的HDL示例,针对Altera和Xilinx的现场可编程门阵列测试了标识符(最长不超过2,048个字符)的混淆代码。报告编译器损失以及FFT运行时结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号