• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1447-1456
• /
• 2019

As artificial intelligence technology is actively used in image processing, it is possible to generate high-quality fake images based on deep learning. Fake images generated using GAN(Generative Adversarial Network), one of unsupervised learning algorithms, have reached levels that are hard to discriminate from the naked eye. Detecting these fake images is required as they can be abused for crimes such as illegal content production, identity fraud and defamation. In this paper, we develop a deep-learning model based on CNN(Convolutional Neural Network) for the detection of StyleGAN fake images. StyleGAN is one of GAN algorithms and has an excellent performance in generating face images. We experiment with 48 number of experimental scenarios developed by combining parameters of the proposed model. We train and test each scenario with 300,000 number of real and fake face images in order to present a model parameter that improves performance in the detection of fake faces.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.199-223
• /
• 2016

As social networking services (SNS) become widely used tools for maintaining social relationships, people use SNS to express themselves online. Users are free to form multiple characters in SNS because of online anonymity. This phenomenon causes SNS users to easily demonstrate multiple personas that are different from their identities in the real world. Therefore, this study focuses on online multi-personas that establish multiple fake identities in the SNS environment. The main objective of this study is to investigate factors that affect online multi-personas. Fake online identities can have various negative consequences such as cyber bullying, cyber vandalism, or antisocial behavior. Since the boundary between the online and offline worlds is fading fast, these negative aspects of online behavior may influence offline behaviors as well. This study focuses on teenagers who often create multi-personas online. According to previous studies, personal identities are usually established during a person's youth. Based on data on 664 teenage users, this study identifies four emotional factors, namely, closeness with others, relative deprivation, peer pressure and social norms. According to data analysis results, three factors (except closeness with others) have positive correlations with users' multi-personas. This study contributes to the literature by identifying the factors that cause young people to form online multi-personas, an issue that has not been fully discussed in previous studies. From a practical perspective, this study provides a basis for a safe online environment by explaining the reasons for creating fake SNS identities.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.127-133
• /
• 2021

Today, phishing attacks represent one of the biggest security threats targeting users of the digital world. They consist of an attempt to steal sensitive information, such as a user's identity or credit and debit card details, using various methods that include fake emails, fake websites, and fake social media messages. Protecting the user's security and privacy therefore becomes complex, especially when those users are children. Currently, children are participating in Internet activity more frequently than ever before. This activity includes, for example, online gaming, communication, and schoolwork. However, children tend to have a less well-developed knowledge of privacy and security concepts, compared to adults. Consequently, they often become victims of cybercrime. In this paper, the effects of security awareness on users who are children are investigated, looking at their ability to detect phishing attacks in social media. In this approach, two Experiments were conducted to evaluate the effects of security awareness on WhatsApp application users in their daily communication. The results of the Experiments revealed that phishing awareness training has a significant positive effect on the ability of children using WhatsApp to identify phishing messages and thereby avoid attacks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6214-6242
• /
• 2019

Routing in mobile ad hoc networks is performed in a distributed fashion where each node acts as host and router, such that it forwards incoming packets for others without relying on a dedicated router. Nodes are mostly resource constraint and the users are usually inclined to conserve their resources and exhibit selfish behaviour by not contributing in the routing process. The trust and reputation models have been proposed to motivate selfish nodes for cooperation in the packet forwarding process. Nodes having bad trust or reputation are detected and secluded from the network, eventually. However, due to the lack of proper identity management and use of non-persistent identities in ad hoc networks, malicious nodes can pose various threats to these methods. For example, a malicious node can discard the bad reputed identity and enter into the system with another identity afresh, called whitewashing. Similarly, a malicious node may create more than one identity, called Sybil attack, for self-promotion, defame other nodes, and broadcast fake recommendations in the network. These identity-based attacks disrupt the overall detection of the reputation systems. In this paper, we propose a reputation-based scheme that detects selfish nodes and deters identity attacks. We address the issue in such a way that, for normal selfish nodes, it will become no longer advantageous to carry out a whitewash. Sybil attackers are also discouraged (i.e., on a single battery, they may create fewer identities). We design and analyse our rationale via game theory and evaluate our proposed reputation system using NS-2 simulator. The results obtained from the simulation demonstrate that our proposed technique considerably diminishes the throughput and utility of selfish nodes with a single identity and selfish nodes with multiple identities when compared to the benchmark scheme.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.649-651
• /
• 2021

In recent years, O2O services for real estate sales are widely distributed in web platforms and apps. This allows sellers, buyers, and real estate brokers to quickly and conveniently conduct real estate sales and charter contracts. However, in the O2O-based real estate sales information system, it wastes time and money for real estate buyers due to the posting of fake information, partial correction of the sales information, and intentional non-posting of the sales information. Therefore, we propose a method of detecting the false or not of real estate property information that can occur on the web platform, and design and implement a proposal system for this. To this end, we propose a method of detecting personal identity and property information based on DID, a distributed identity authentication protocol. The false real estate sales information detection system proposed by us can determine the existence of real estate sales information, partially correct the false sales information, or prove whether or not intentionally unpublished in three steps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.10
• /
• pp.2544-2560
• /
• 2013

As a cornerstone of the next generation air traffic management (ATM), automatic dependent surveillance-broadcast (ADS-B) system can provide continual broadcast of aircraft position, identity, velocity and other messages over unencrypted data links to generate a common situational awareness picture for ATM. However, since ADS-B messages are unauthenticated, it is easy to insert fake aircrafts into the system via spoofing or insertion of false messages. Unfortunately, the authentication for ADS-B messages has not yet been well studied. In this paper, we propose an efficient broadcast authentication scheme with batch verification for ADS-B messages which employs an identity-based signature (IBS). Security analysis indicates that our scheme can achieve integrity and authenticity of ADS-B messages, batch verification, and resilience to key leakage. Performance evaluation demonstrates that our scheme is computationally efficient for the typical avionics devices with limited resources, and it has low communication overhead well suitable for low-bandwidth ADS-B data link.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.592-599
• /
• 2010

In recent years, significant improvements have been made to the techniques used for analyzing satellite communication and attacking satellite systems. In 2003, a research team at Los Alamos National Laboratory, USA, demonstrated the ease with which civilian global positioning system (GPS) spoofing attacks can be implemented. They fed fake signals to the GPS receiver so that it operates as though it were located at a position different from its actual location. Moreover, Galileo in-orbit validation element A and Compass-M1 civilian codes in all available frequency bands were decoded in 2007 and 2009. These events indicate that cryptography should be used in addition to the coding technique for secure and authenticated satellite communication. In this study, we address this issue by using an authenticated key-exchange protocol to build a secure and authenticated communication channel for satellite communication. Our protocol uses identity-based cryptography. We also prove the security of our protocol in the extended Canetti-Krawczyk model, which is the strongest security model for authenticated key-exchange protocols, under the random oracle assumption and computational Diffie-Hellman assumption. In addition, our protocol helps achieve high efficiency in both communication and computation and thus improve security in satellite communication.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6243-6259
• /
• 2019

As a foundation of next-generation air transportation systems, automatic dependent surveillance-broadcast (ADS-B) helps pilots and air traffic controllers create a safer and more efficient national airspace system. Owing to the open communication environment, it is easy to insert fake aircraft into the system via spoofing or the insertion of false messages. Efforts have thus been made in academic research and practice in the aviation industry to ensure the security of transmission of messages of the ADS-B system. An identity-based batch verification (IBV) scheme was recently proposed to enhance the security and efficiency of the ADS-B system, but current IBV schemes are often too resource intensive because of the application of complex hash-to-point operations or bilinear pairing operations. In this paper, we propose a lightweight IBV signature scheme for the ADS-B system that is robust against adaptive chosen message attacks in the random oracle model, and ensures the security of batch message verification and against the replaying attack. The proposed IBV scheme needs only a small and constant number of point multiplication and point addition computations instead of hash-to-point or pairing operations. Detailed performance analyses were conducted to show that the proposed IBV scheme has clear advantages over prevalent schemes in terms of computational cost and transmission overhead.

• The Journal of the Korea Contents Association
• /
• v.22 no.7
• /
• pp.548-562
• /
• 2022

This study was conducted to diagnose the issues of AI ethics in global content and to discuss what kind of discourse is needed to strengthen human identity. To this end, the study selected Netflix original content "The Social Dilemma" for analysis and adopted narrative analysis as the research method. The analysis results confirmed that "Social Dilemma" showed the structure of a traditional current affairs documentary and mainly used experts and statistical data to develop the story. It also reinforced core content claims by enumerating domestic and foreign cases such as the 2021 Myanmar massacre and the spread of fake news. In addition, the relationship between the characters clearly revealed the binary opposition between developers and media companies as well as users and advertisers. For the solution to the problem, strong regulations on businesses and the suspension of social media use were reached. However, "The Social Dilemma" merely pointed out the misuse of AI technology and had a narrative that ignored human identity and social relationships. Such results raise the need for creating contents that emphasize the importance of human sociality, relationships, and learning ability in the age of AI.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.358-368
• /
• 2022

Social media is a window for everyone, individuals, communities, and companies to spread ideas and promote trends and products. With these opportunities, challenges and problems related to security, privacy and rights arose. Also, the data accumulated from social media has become a fertile source for many analytics, inference, and experimentation with new technologies in the field of data science. In this chapter, emphasis will be given to methods of trend analysis, especially ensemble learning methods. Ensemble learning methods embrace the concept of cooperation between different learning methods rather than competition between them. Therefore, in this chapter, we will discuss the most important trends in ensemble learning and their applications in analysing social media data and anticipating the most important future trends.