• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.692-695
• /
• 2024

With the recent advancements in artificial intelligence (AI), the performance of deep learning-based audio deepfake technology has significantly improved. This technology has been exploited for criminal activities, leading to various cases of victimization. To prevent such illicit outcomes, this paper proposes a deep learning-based audio deepfake detection model. In this study, we propose CoNSIST, an improved audio deepfake detection model, which incorporates three additional components into the graph-based end-to-end model AASIST: (i) Squeeze and Excitation, (ii) Positional Encoding, and (iii) Reformulated HS-GAL, This incorporation is expected to enable more effective feature extraction, elimination of unnecessary operations, and consideration of more diverse information, thereby improving the performance of the original AASIST. The results of multiple experiments indicate that CoNSIST has enhanced the performance of audio deepfake detection compared to existing models.

• Journal of Broadcast Engineering
• /
• v.24 no.7
• /
• pp.1266-1275
• /
• 2019

With increasing criminal rates and number of CCTVs, much attention has been paid to intelligent surveillance system on the horizon. Object detection and tracking algorithms have been developed to reduce false alarms and accurately help security agents immediately response to undesirable changes in video clips such as crimes and accidents. Many studies have proposed a variety of algorithms to improve accuracy of detecting and tracking objects outside tunnels. The proposed methods might not work well in a tunnel because of low illuminance significantly susceptible to tail and warning lights of driving vehicles. The detection performance has rarely been tested against the tunnel environment. This study investigated a feasibility of object detection and tracking in an actual tunnel environment by utilizing YOLOv3 and Kernelized Correlation Filter. We tested 40 actual video clips to differentiate pedestrians and motorcycles to evaluate the performance of our algorithm. The experimental results showed significant difference in detection between pedestrians and motorcycles without false positive rates. Our findings are expected to provide a stepping stone of developing efficient detection algorithms suitable for tunnel environment and encouraging other researchers to glean reliable tracking data for smarter and safer City.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.357-358
• /
• 2021

Although many people watch the scene with multiple surveillance cameras, it is difficult to ensure that immediate action can be taken in the event of a crime. Therefore, there is a need for a "crime behavior detection system" that can analyze images in real time from multiple surveillance cameras installed in elevators, call immediate crime alerts, and track crime scenes and times effectively. In this paper, a study was conducted to detect violent scenes occurring in elevators using Scene Change Detection. For effective detection, an x2-color histogram combining color histogram and histogram was applied.

• Journal of forensic and investigative science
• /
• v.1 no.2
• /
• pp.5-19
• /
• 2006

Data mining is an information extraction activity to discover hidden facts contained in databases. Using a combination of machine learning, statistical analysis, modeling techniques and database technology, data mining finds patterns and subtle relationships in data and infers rules that allow the prediction of future results. Typical applications include market segmentation, customer profiling, fraud detection, evaluation of retail promotions, and credit risk analysis. Law enforcement agencies deal with mass data to investigate the crime and its amount is increasing due to the development of processing the data by using computer. Now new challenge to discover knowledge in that data is confronted to us. It can be applied in criminal investigation to find offenders by analysis of complex and relational data structures and free texts using their criminal records or statement texts. This study was aimed to evaluate possibile application of data mining and its limitation in practical criminal investigation. Clustering of the criminal cases will be possible in habitual crimes such as fraud and burglary when using data mining to identify the crime pattern. Neural network modelling, one of tools in data mining, can be applied to differentiating suspect's photograph or handwriting with that of convict or criminal profiling. A case study of in practical insurance fraud showed that data mining was useful in organized crimes such as gang, terrorism and money laundering. But the products of data mining in criminal investigation should be cautious for evaluating because data mining just offer a clue instead of conclusion. The legal regulation is needed to control the abuse of law enforcement agencies and to protect personal privacy or human rights.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1687-1692
• /
• 2009

Cyber forensics is used the process and technology of digital forensics as a criminal investigation in cyber space. Cyber crime is classified into cyber terror and general cyber crime, and those two classes are connected with each other. The investigation of cyber terror requires high technology, system environment and experts, and general cyber crime is connected with general crime by evidence from digital data in cyber space. Accordingly, it is difficult to determine relational crime types, collect evidence and the legal admissibility of evidence. Therefore, we considered the classifications of cyber crime, the collection of evidence in cyber space and the application of laws to cyber crime. In order to efficiently investigate cyber crime, it is necessary to integrate those concepts for each cyber crime-case. In this paper, we constructed a cyber forensics domain ontology for cyber criminal investigation using the concepts, relations and properties, according to categories of cyber crime, laws, evidence, and information of criminals and crime-cases. This ontology can be used in the process of investigating of cyber crime-cases, and for data mining of cyber crime; classification, clustering, association and detection of crime types, crime cases, evidences and criminals.

• Bulletin of the Korean Chemical Society
• /
• v.34 no.5
• /
• pp.1457-1461
• /
• 2013

The $Fe_3O_4$-core and Ag-shell ($Fe_3O_4@Ag$ nanoeggs) were prepared through the encapsulation of 3-aminopropyltriethoxysilane-coated magnetite nanoparticle in nano-Ag shell by a simple chemically controlled procedure. The $Fe_3O_4@Ag$ nanoeggs were characterized by scanning electron microscopy, transmission electron microscopy, UV-vis spectrum and superconducting quantum interference device magnetometer, respectively. A detailed analysis is provided of how the hydrolysis and condensation of 3-aminopropyltriethoxysilane and the pH value are vital in fabricating the $Fe_3O_4@Ag$ nanoeggs. The prepared $Fe_3O_4@Ag$ nanoeggs possessed uniform size, improved monodispersity, stability against aggregation and high magnetization, which were utilized for the detection of latent fingerprints deposited onto different surfaces. The experimental results showed that the latent fingerprints developed with the $Fe_3O_4@Ag$ nanoeggs powders exhibited excellent ridge details with minimal background staining.

• Analytical Science and Technology
• /
• v.24 no.1
• /
• pp.45-50
• /
• 2011

While the crime scene investigation, evidences are found to search with the naked eyes and to use science equipments. Crime evidences, which are used as judgement, have various things: blood, sperm, saliva, hair, fingerprint, fiber, soil, paint, and so on, especially, fingerprints could take through crime scene investigation, and in there, it could distinguish individually. In this case study, sort of leathers: a wallet, a belt, and a sofa, which are needed special identification even thought people experience easily in usual day, are tried many of the identification tests. As a result, using fluorescent magnetic powder method or fluorescent powder method as identification of many leathers is most efficient.

• The Korean Society of Law and Medicine
• /
• v.13 no.1
• /
• pp.41-69
• /
• 2012

First introduced in 1977, Korean health care system reached to national coverage in short period of time never seen before in any other countries, and rated as successful system protecting the health of the public at relatively low price. However, despite those positive evaluations, some of fraudulent medical organizations or pharmacies are hindering the sound development of the national health care system with meticulous false billing exaggerating the number of patients or the days of their treatment. To prevent aforementioned nursing home fraud and false billing, the misconduct should be punished as subject to the criminal law and severally punished for fines and payments which far exceed the expected amount of illicit gains as it is basically violation of criminal fraud, other than the forced return of illicit gains based on civil laws. Furthermore, the Health Insurance Review and Assessment Service should strengthen and complement the fraud investigators, the review process, and the professional training to raise the detection rates. It might also want to review ways to implement whistleblower rewarding system and rewards for evidences of healthcare fraud to overcome the limits of external review.

• Analytical Science and Technology
• /
• v.26 no.4
• /
• pp.228-234
• /
• 2013

Methamphetamine is an amine-containing illegal drug and is distributed unlawfully in South Korea. Finding a rapid, convenient and semi-quantitative determination method for methamphetamine is a very important issue in the area of forensic drug testing. As an effort to develop new screening method, the reactions between three organic compounds which are structurally similar to methamphetamine and N-(9-fluorenylmethoxycarbonyloxy) succinimide (FMOC-NHS) were performed on silica gel ($SiO_2$) TLC plates. Three reference compounds were synthesized and used for the identification, comparison and study of the limit of detection (LOD) of the products obtained from a direct reaction on a TLC plate. As a result, FMOC-NHS as a derivatization reagent generated compounds containing highly UV-active functional groups on the TLC plate after reacting with primary- and secondary amines. In the experiment 2D the LOD of amines was in the range of 0.045 and 0.01 mg/mL ($2{\mu}L/spot$), and in 1D the LOD was in the range of 0.002 and 0.007 mg/mL ($2{\mu}L/spot$). The LODs of the compounds tested were dependent on the concentration of the derivatizing reagent.

• Korean Journal of Forensic Psychology
• /
• v.11 no.2
• /
• pp.173-190
• /
• 2020

The purpose of this study is to verify whether it is possible for participants to discriminate between innocent and guilty suspects when they are exposed to criminal information utilizing an autobiographical implicit association test (aIAT). A total of 49 college students were randomly assigned to guilty group, innocent-aware group, or innocent-unaware group. Participants performed an aIAT to detect suspects after performing either mock crime or control task. It was verified that innocent suspect and guilty suspect exposed with crime information could be distinguished through D-score and reaction time, converted to symbolize strength of the association between guilty sentences, innocent sentences, and truth sentences. As a result of the analysis, guilty group showed significantly higher D-score than both innocent-aware group and innocent-unaware group. guilty group also showed faster response time in true-guilty condition than true-innocent condition. This shows that the association of true-guilty conditions is stronger than that of true-innocent conditions. On the other hand, the innocent-aware group showed a faster response time in the true-innocent condition than the true-guilty condition, and innocent-unaware group showed no significant difference between the two conditions. Through this, it was confirmed that innocent suspects exposed to criminal information can be discriminated according to the aIAT pattern, which has a faster reaction rate to the truth and innocence union than the guilty group. This study confirmed that suspects exposed to criminal information can be effectively discriminated using aIAT, and further suggests the usefulness and potential of aIAT in the field of lie detection.