• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.11-20
• /
• 2024

While artificial neural networks are adept at identifying patterns, they can struggle to distinguish between actual correlations and false associations between extracted facial features and criminal behavior within the training data. These associations may not indicate causal connections. Socioeconomic factors, ethnicity, or even chance occurrences in the data can influence both facial features and criminal activity. Consequently, the artificial neural network might identify linked features without understanding the underlying cause. This raises concerns about incorrect linkages and potential misclassification of individuals based on features unrelated to criminal tendencies. To address this challenge, we propose a novel region-based training approach for artificial neural networks focused on criminal propensity detection. Instead of solely relying on overall facial recognition, the network would systematically analyze each facial feature in isolation. This fine-grained approach would enable the network to identify which specific features hold the strongest correlations with criminal activity within the training data. By focusing on these key features, the network can be optimized for more accurate and reliable criminal propensity prediction. This study examines the effectiveness of various algorithms for criminal propensity classification. We evaluate YOLO versions YOLOv5 and YOLOv8 alongside VGG-16. Our findings indicate that YOLO achieved the highest accuracy 0.93 in classifying criminal and non-criminal facial features. While these results are promising, we acknowledge the need for further research on bias and misclassification in criminal justice applications

• Journal of Information Processing Systems
• /
• v.10 no.1
• /
• pp.1-22
• /
• 2014

Recent technological advances provide the opportunity to use large amounts of multimedia data from a multitude of sensors with different modalities (e.g., video, text) for the detection and characterization of criminal activity. Their integration can compensate for sensor and modality deficiencies by using data from other available sensors and modalities. However, building such an integrated system at the scale of neighborhood and cities is challenging due to the large amount of data to be considered and the need to ensure a short response time to potential criminal activity. In this paper, we present a system that enables multi-modal data collection at scale and automates the detection of events of interest for the surveillance and reconnaissance of criminal activity. The proposed system showcases novel analytical tools that fuse multimedia data streams to automatically detect and identify specific criminal events and activities. More specifically, the system detects and analyzes series of incidents (an incident is an occurrence or artifact relevant to a criminal activity extracted from a single media stream) in the spatiotemporal domain to extract events (actual instances of criminal events) while cross-referencing multimodal media streams and incidents in time and space to provide a comprehensive view to a human operator while avoiding information overload. We present several case studies that demonstrate how the proposed system can provide law enforcement personnel with forensic and real time tools to identify and track potential criminal activity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.250-251
• /
• 2013

In this paper, we would like to extract criminals doing this criminal offense to smoke in elevators. Extraction method detect difference value using modified color-$X^2$-test and it was normalized. Next, we find frames that has occurred scene change in successive frames using the four-step algorithm of scene change detection. Finally, we present the method of smoking image retrieval and extraction in stored large amount of video.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.89-95
• /
• 2013

Smoking in elevators is a criminal offense that is included in a misdemeanor. Because of that smoking in elevators can be very critical for our growing children and weak women. In this paper, we would like to extract criminals doing this criminal offense to smoke in elevators. Extraction method detect difference value using modified color-X2-test and it was normalized. Next, we find frames that has occurred scene change in successive frames using the four-step algorithm of scene change detection. Finally, we present the method of smoking image retrieval and extraction in stored large amount of video. In the experiment, we show process and number of scene change detection, and the number of video searched per retrieval time. The extracted smoking video is to submit as evidence for the police or court.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.237-242
• /
• 2008

This study aims to provide theoretical base in criminal law for engineers in the viewpoint of jurists to encourage interdisciplinary studies on cyber crimes. Apart from seriousness of discussion on torrent cyber crimes, a good effect of the internet networks such as sharing of information has bee emphasized while the evil influence of its side effect has been neglected. Therefore, this study suggests that we need to consider reinforcement of cyber ethics, and legal mind of IT technicians, strict security by managers, active efforts to develop legitimate contents by managers of web hardware and P2P, and reinforcement of punishments against crimes by internet users. And this study approaches new norms on computer and cyber crimes in interpretational sense of criminal law, and provides the theoretical base of the criminal law focusing on traditional theories, assumptions, and precedents involved in regulations against computer virus distribution.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.4
• /
• pp.723-736
• /
• 2022

Steganography is being used as a means of secret communication for crimes that threaten national security such as terrorism and espionage. With the development of computers, steganography technologies develop and criminals produce and use their own programs. However, the research for steganography is not active because detailed information on national security cases is not disclosed. The development of investigation technologies and the responses of criminal law are insufficient. Therefore, in this paper, the detection and decoding process was examined for steganography investigation, and the method was analyzed for 'the spy case of Pastor Kim', who was convicted by the Supreme Court. Multiple security devices were prepared using symmetric steganography using the pre-promised stego key. Furthermore, the three criminal legal issues: (1) the relevance issue, (2) the right to participate, and (3) the public trial issue a countermeasure were considered in national security cases. Through this paper, we hope that the investigative agency will develop analysis techniques for steganography.

• Analytical Science and Technology
• /
• v.20 no.2
• /
• pp.155-163
• /
• 2007

Porosity paper evidence is encountered in case of forgery, kidnapping, fraud and terrorist activity. The present study was designed to evaluate the effect of three chemical reagents (Ninhydrin, 1,8-diazafluoren-9-one (DFO), Iodine fuming) to the quality of developed latent fingerprints on porosity printing papers and newspaper. In case of printing papers, print quality was better with Iodine fuming method than Ninhydrin and DFO treatment to developing latent fingerprints. Developing latent fingerprint on newspapers was achieved with Iodine fuming processing. The processing of Iodine fuming followed by DFO and by using blue light (orange red filter) exhibited better results with Iodine fuming. Enhancement of latent fingerprint detection image using Digital Imaging System was achieved.

• Analytical Science and Technology
• /
• v.23 no.2
• /
• pp.216-223
• /
• 2010

In previous research, results on efficiency versus size and type of Ag particles showed similarity of detection efficiency comparing the particles of flake and spherical type with the gray particle on the market and in the case of nAg (rod, $0.9\;{\mu}m$) particle, relatively good results was given in the various evaluation methods for detection efficiency of latent fingerprint. However, oxidation was occurred when nAg particles laying on nature condition for a month and due to water absorption, detection efficiency was decreased. Therefore, with need to prevent oxidation and water absorption, more research is necessary. In this research, surface modification on nAg particles using silicon oil was conducted in various methods for complementing weakness of oxidation and water absorption. Then detection efficiency of nAg particles and surface modified nAg particles was evaluated by the number of feature points on the surface of non-porous materials (glass, plastic etc.) and degree of particle adhesion with ridges and contrast of detected fingerprint. Improvement of preventing oxidation and water absorbtion was given by surface modification using silicon oil (DC200, 0.5%) on the surface of non-porous materials.

• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.520-537
• /
• 2019

This paper proposes a system that can detect the data leakage pattern using a convolutional neural network based on defining the behaviors of leaking data. In this case, the leakage detection scenario of data leakage is composed of the patterns of occurrence of security logs by administration and related patterns between the security logs that are analyzed by association relationship analysis. This proposed system then detects whether the data is leaked through the convolutional neural network using an insider malicious behavior graph. Since each graph is drawn according to the leakage detection scenario of a data leakage, the system can identify the criminal insider along with the source of malicious behavior according to the results of the convolutional neural network. The results of the performance experiment using a virtual scenario show that even if a new malicious pattern that has not been previously defined is inputted into the data leakage detection system, it is possible to determine whether the data has been leaked. In addition, as compared with other data leakage detection systems, it can be seen that the proposed system is able to detect data leakage more flexibly.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.103-104
• /
• 2014

본 논문에서는 범죄 행위중 하나인 흡연을 엘리베이터 내에서 행하는 범죄자를 추출하고자 한다. 추출 방법은 변형된 컬러-$X^2$ 히스토그램을를 이용하여 차이값을 추출하고 정규화를 수행한다. 그러고 나서 4-단계의 장면 전환 검출 알고리즘을 이용하여 연속적인 프레임들에서 장면 전환이 발생한 지점을 찾아낸다. 끝으로, 비디오에 저장된 대량의 영상에서 흡연 영상의 검색 및 추출을 위한 방법을 제시한다.