Search

The pervasive influence of social networks on information dissemination necessitates robust strategies for understanding and mitigating the spread of rumors within these interconnected ecosystems. This research endeavors to address this imperative through the application of a graph neural network (GNN) model, designed to capture intricate relationships among users and content in social networks. The study integrates user-level attributes, content characteristics, and network structures to develop a comprehensive model capable of predicting the likelihood of rumor propagation. The proposed model is situated within a broader conceptual framework that incorporates sociological theories on information diffusion, user behavior, and network dynamics. The results of this research offer insights into the interpretability of the GNN model's predictions and lay the groundwork for future investigations. The iterative refinement of the model, consideration of ethical implications, and comparison against traditional machine learning baselines emerge as crucial steps in advancing the understanding and application of deep learning methodologies for rumor control in social networks. By embracing the complexities of real-world scenarios and adhering to ethical standards, this research strives to contribute to the development of proactive tools for rumor management, fostering resilient and trustworthy online information ecosystems. [ABSTRACT FROM AUTHOR]

Information and communication security has become more crucial and has become a new problem in relation to security, accessibility, data management, and other information policy challenges as a result of how easy it is for all users to use communication media. One of the fields of science that has a technique or art for disguising the data sent by the sender to the recipient with the aim of maintaining the confidentiality of the data is called cryptography. In determining better cryptographic algorithms for data security systems, in addition to considering strength, key length and ciphertext enlargement are also important factors to consider. Therefore, in this study, we attempted to compare the ciphertext magnification of the generalization of the ElGamal and multi-factor RSA algorithms by utilizing the same key length. Generalization of the ElGamal and Multi-factor RSA are both asymmetric algorithms that have public and private key pairs for encryption and decryption. However, at the level of security the RSA algorithm is based on the difficulty of finding large integer factors into two prime factors. In contrast to the ElGamal algorithm, security is based on the difficulty of calculating the discrete logarithm of a large prime modulus. The results of the comparison algorithm carried out are represented in the form of a table containing the plaintext, key length, and size of the data. [ABSTRACT FROM AUTHOR]

Cryptography is a technique for encoding data by encrypting plaintext into an unreadable (meaningless) form. Cryptographic methods have good and bad performance depending on the type of algorithm we use. Therefore, the purpose of this study is to measure speed by combining the two algorithms used. The Rabbit Stream algorithm is a stream cipher algorithm whose system security depends on the generation of a key bit stream (keystream), which only guarantees 128-bit key security but has the advantage of being fast in the encryption and decryption process, while the Enhanced Dual RSA algorithm is an asymmetric algorithm to increase data protection from the Dual RSA algorithm by utilizing the Pells equation as a substitute for public key exponents. On the other hand, the algorithm in question requires a significant amount of time to encrypt messages with a large capacity when compared to the Rabbit Stream algorithm. Nonetheless, the study's findings suggest that using a hybrid method is comparatively faster for processing substantial amounts of data. [ABSTRACT FROM AUTHOR]

Uploading an identity card as an image for the account verification process or transactions online can be a threat to application users. Identity card theft can be carried out by irresponsible persons if the application can be hacked. Therefore, protection of the image is required for authentication. In this study, the proposed technique is watermarking. A watermark in the form of a binary image will be embedded into the image as ownership using a Discrete Cosine Transform. The Discrete Cosine Transform works in the frequency domain. The location of the embedding of different watermarks was analysed in each 8×8 DCT block. The results of the analysis to assess the imperceptibility of original images and watermarked images using PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index Measure), while assessing the watermark robustness embedded using NCC (Normalized Cross Correlation). The results show PSNR (Peak Signal to Noise Ratio) = 54 dB with a watermark strength of 0,1 and an average SSIM (Structural Similarity Index Measure) = 0,9 on 4 scanned images in BMP format with a resolution of 100 DPI. A good watermark embedding is done on the green component at middle frequencies to maintain a balance between imperceptibility and robustness. In contrast, the red component at low frequency is vulnerable to attacks in the form of brightness +20 and contrast +50 with an average NCC (Normalized Cross Correlation) = 0,85. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of suboptimal biological control of the Aedes aegypti mosquito, which serves as a vector for Dengue, Chikungunya, and Zika viruses. These arthropods pose a significant threat to approximately one-third of the global population annually, capable of causing severe pain, hemorrhagic fever, and brain defects in unborn children with a single bite. The research introduces a technologically effective solution employing deep neural networks (DNNs) to conduct surveys during the immature larval stage. Our approach enables automatic identification of the biological vector in the larval stage, achieving a higher accuracy of 81.7% in region-of-interest segmentation. Moreover, it classifies larvae as Aedes positive or negative with an accuracy of 97%, significantly reducing response time from days to seconds without human intervention. The proposed solution is costeffective, minimizing the need for trained entomologists, laboratories, and expensive equipment. Utilizing microscopebased image acquisition hardware, a computer with CPU hardware, and a petri dish, sample capture and analysis become straightforward. The advantages of this proposal are particularly valuable in underdeveloped countries and remote regions, where economic constraints may limit access to preventive health services and biological vector control. [ABSTRACT FROM AUTHOR]