지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2012.10
- 수록면
- 289 - 293 (5page)
이용수
초록· 키워드
오류제보하기
Several tools are available for reverse engineering Windows portable executable (PE) files. The first step of reverse engineering is to disassemble the PE file. However, files sometimes do not load or open correctly due an incorrect PE file format. We therefore developed an algorithm that restores the PE file structure of an incorrectly formatted PE file. The program that uses this algorithm loads the file to memory, reconstructs the file format automatically, and then saves the new file. However, processing of many large files can result in performance degradation. We therefore adopted a parallel programming technique that uses open multi-processing (OpenMP) to simultaneously process large files. For parallel programming, we used thread level parallelism and data decomposition. We compared the performance of a sequential implementation of our algorithm and two parallel implementations of the algorithm by evaluating execution time, CPU usage, and concurrency for three different files using Visual Studio’s Profiler and Intel Parallel Studio 2011. Parallel processing reduced execution time by about 75% compared to sequential processing.
목차
Abstract
1. INTRODUCTION
2. PE FILE FORMAT
3. PE FILE RECOVERY ALGORITHM
4. EXPERIMENT
5. CONCLUSIONS
REFERENCES
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
최근 본 자료
댓글(0)
0