• Broadcasting and Media Magazine
• /
• v.25 no.2
• /
• pp.52-60
• /
• 2020

최근 생체 정보를 이용한 사용자 인증 기술이 발전하면서 이를 모바일 기기에 적용하는 사례가 크게 증가하고 있다. 특히, 얼굴 기반 인증 방식은 비접촉식이며 사용이 편리하여 적용 범위가 점점 확대되고 있는 추세이다. 그러나, 사용자의 얼굴 사진이나 동영상 등을 이용한 위변조가 용이하기 때문에 모바일 기기 내 보안 유지에 어려움을 야기한다. 본 고에서는 이러한 문제를 해결하기 위해 최근 활발히 연구되고 있는 심층신경망 기반 얼굴 위변조 검출 연구의 최신 동향을 소개하고자 한다. 먼저, 기본 합성곱 신경망 구조부터 생성모델 기반의 위변조 검출 방법까지 다양한 신경망 구조를 이용한 위변조 검출 방법에 대해 설명한다. 또한, 심층신경망 학습을 위해 사용되는 얼굴 위변조 데이터셋에 대해서도 간략히 살펴보고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.181-183
• /
• 2005

저작권 보호 기술의 하나인 디지털 워터마킹은 디지털 콘텐츠에 삽입되어 저작권 확인 및 증명에 이용될 뿐만 아니라 영상의 위변조 판별에도 이용된다. 즉, 영상이 변조되는 경우 삽입된 워터마크가 변형됨으로써 위변조 여부 및 위변조 영역의 확인도 가능하다. 본 논문에서는 이와 같이 영상의 위변조 여부를 판별하기 위한 인증 워터마킹 기법으로 적응적인 양자화 워터마킹 기법을 제안한다. 워터마크 삽입 과정은 영상에 DWT를 수행한 뒤 저주파 영역에 블록 DCT를 수행하여 계수들을 변형시키는 방법으로 수행되며, 이를 위해 원신호의 파워를 고려한 적응적인 양자화 방식을 제안하였다. 실험 결과 제안 방식에 의해 워터마크 삽입된 영상은 화질적으로 원영상과 차이가 없고 압축에 대한 강인성도 우수하여 인증 워터마킹에 적합함을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.344-347
• /
• 2012

디지털 고성능 영상장비의 대중화와 강력한 이미지 편집 소프트웨어의 출현으로 인해 고화질의 위 변조지폐를 누구나 쉽게 제조 가능하게 되었다. 그러나 일반인의 위 변조지폐 발견비율은 낮은 수준이다. 본 논문에서는 범용 스캐너를 이용하여 위 변조지폐를 판별할 수 있는 시스템을 제안한다. 본 시스템에서는 위 변조지폐를 출력하는 과정에서 나타나는 인쇄물의 고유한 특징에 기반하여 위 변조 여부를 판별한다. 비지역적 평균 알고리즘을 이용하여 노이즈 특성을 추출하고, 명암도 작용길이 행렬을 계산하여 지폐의 특성을 추출하였다. 제안한 알고리즘의 성능을 분석하기 위해 총 324장의 1만원권 지폐와 위조지폐 이미지로 실험하였으며, 그 결과 제안한 알고리즘이 위 변조 판별에 있어서 92% 이상을 보임을 확인하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.545-551
• /
• 2023

As digital information is readily available to everyone today, the adoption of digital evidence is increasing. However, it is virtually impossible to determine the authenticity of forgery in the case of a voice recording file that has gone through a sophisticated editing process along with the spread of various voice file editing tools. This study aims to prove that forgery, which is difficult to distinguish from the original file, is possible by using insertion, deletion, linking, and synthetic editing technologies in voice recording files. This study presents the difficulty of detecting forgery by encoding a forged voice file with the same extension as the original. In addition, it was shown that forgery detection is impossible if additional transition band deletion and secondary encoding are performed only for experiments in which features occurred. Through this, this study is expected to contribute to the establishment of more stringent evidence admissibility criteria for adopting voice recording files as digital evidence.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.807-812
• /
• 2022

Recently, as the number of voice recording files submitted as court evidence increases, the number of cases claiming forgery is also increasing. If the audio recording file structure and metadata, which are objective grounds, are completely forged, it is actually impossible to detect forgery of the sophisticated audio recording file. It is extremely rare for the court to reject the file structure and metadata analysis performed with the forged audio recording file. The purpose of this study is to prove that forgery of voice recording file structure and metadata is easily possible. To this end, in this study, it was introduced that forgery detection is impossible when the 'mixed paste' function, which enables sophisticated editing based on the typification of the editing method of voice recording files, is applied. Moreover, it has been proven through experiments that forgery of file structure and metadata is possible. Therefore, a stricter standard for judging the admissibility of evidence is required when the audio recording file is adopted as digital evidence. This study will not only contribute to the standard of integrity in the adoption of digital evidence by judges, but will also contribute to the method of constructing a dataset for artificial intelligence in detecting forgery of recorded files that is expected to be developed in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.55-64
• /
• 2013

Due to the popularization of digital high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy for anyone to make a high-quality counterfeit money. However, the probability of detecting a counterfeit money to the general public is extremely low. In this paper, we propose a counterfeit money detection algorithm using a general purpose scanner. This algorithm determines counterfeit money based on the different features in the printing process. After the non-local mean value is used to analyze the noises from each money, we extract statistical features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and test the support vector machine classifier for identifying either original or counterfeit money. In the experiment, we use total 324 images of original money and counterfeit money. Also, we compare with noise features from previous researches using wiener filter and discrete wavelet transform. The accuracy of the algorithm for identifying counterfeit money was over 94%. Also, the accuracy for identifying the printing source was over 93%. The presented algorithm performs better than previous researches.

• Journal of Convergence Society for SMB
• /
• v.5 no.3
• /
• pp.27-31
• /
• 2015

As the number of smartphone users is increasing with the development of mobile devices, the range of monetary transaction from the individual use is increasing. Therefore, hacking methods are diversified and the information forgery of mobile devices has been a current issue. The forgery via apps in mobile devices is a hacking method that creates an app similar to well-known apps to deceive the users. The forgery attack corresponds to the violation of integrity, one of three elements of security. Due to the forgery, the value and credibility of an app decreases with the risk increased. With the forgery in app, private information and data can be stolen and the financial losses can occur. This paper examined the forgery, and suggested a way to detect it, and sought the countermeasure to the forgery.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.11a
• /
• pp.444-448
• /
• 2007

이차원바코드 기술과 암호화 알고리즘을 이용하여 문서의 위${\cdot}$변조 등을 방지하고 문서의 상태를 기업체나 공공기관 등에서 쉽게 확인하여 판단할 수 있는 시스템을 제안한다. 모든 위${\codt}$변조 확인이 필요한 문서에 암호화된 이차원바코드를 첨부한다. 확인자 측에서는 첨부된 이차원 바코드를 바코드 리더기로 인식하거나 이차원 바코드의 사진을 관련 인터넷 웹 사이트를 통해 문서의 위${\cdot}$변조를 판단한다.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.547-558
• /
• 2014

Recently, in the course of business processes a variety of abuse cases of fax documents is common in general corporate, government, and financial institutions. To solve this problem, it is necessary for a technique to prevent falsification of fax documents. In this paper, we propose a new fax sender verification technique based on pattern analysis to prevent falsification of fax documents only using the received fax document. In the proposed technique, the fax sender is verified by analyzing the communication signal patterns between the fax sender and receiver and image pattern in the received fax document. In this paper, we conduct the experiments that apply our technique to real-world fax systems, and then tamper-proof effects were confirmed from the experimental results.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.889-898
• /
• 2013

Due to the popularization of high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy to make high-quality counterfeit money. However, the probability of detecting counterfeit money to the general public is extremely low and the detection device is expensive. In this paper, a counterfeit money detection algorithm using a general purpose scanner and computer system is proposed. First, the printing features of color printers are calculated using morphological operations and gray-level co-occurrence matrix. Then, these features are used to train a support vector machine classifier. This trained classifier is applied for identifying either original or counterfeit money. In the experiment, we measured the detection rate between the original and counterfeit money. Also, the printing source was identified. The proposed algorithm was compared with the algorithm using wiener filter to identify color printing source. The accuracy for identifying counterfeit money was 91.92%. The accuracy for identifying the printing source was over 94.5%. The results support that the proposed algorithm performs better than previous researches.