Style matching CAPTCHA: match neural transferred styles to thwart intelligent attacks

Ray, Palash; Bera, Asish; Giri, Debasis; Bhattacharjee, Debotosh

doi:10.1007/s00530-023-01075-0

Cited by 2 publications

(2 citation statements)

References 86 publications

(116 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to The et al [13], the integration of computer vision and metaverse has exhibited a growing level of dynamism. The integration of AI and AR/VR technologies has led to the prominence of computer vision as a crucial element in the creation of immersive, interactive, and intelligent settings within the metaverse [14,15]. The convergence of this particular domain has been of utmost significance in various domains, including user engagement, content generation, and safeguarding measures [16].…”

Section: Historical Overviewmentioning

confidence: 99%

Computer vision meets metaverse

Zakynthinou,

Kanakaris,

Vrochidou

et al. 2024

View full text Add to dashboard Cite

<p>This comprehensive analysis delves into the historical progression and important technological and contemporary advancements of computer vision inside the metaverse. The metaverse, which can be characterized as an interactive virtual reality environment that mirrors the physical world, signifies a novel domain for the utilization of computer vision in various applications. These applications span from object identification and tracking to gesture recognition and augmented reality. Additionally, a thorough evaluation of specific case studies occurs to provide a deeper understanding of the subject. Despite notable progress, the incorporation and utilization of computer vision inside the metaverse present numerous obstacles, including computational expenses, apprehensions regarding data privacy, and the faithful replication of physical aspects of reality. Potential solutions are examined, including deep learning approaches, optimization strategies, and the formation of ethical guidelines. A comprehensive analysis of anticipated patterns within the industry is also included, with emphasis on the confluence of artificial intelligence, the Internet of Things, and blockchain technologies. These convergences are predicted to create substantial prospects for the advancement of the metaverse. This review culminates by offering a contemplation on the ethical considerations and duties that arise from the utilization of computer vision in the realm beyond mortal existence. Research findings demonstrate that these technologies have greatly augmented user engagement and immersion within the digital domain. Readers can enhance their understanding of the interdependent connection between computer vision and the metaverse through the present analysis of existing scholarly works. Thus, this study aspires to make a valuable contribution to the advancement of research in this new domain.<strong></strong></p>

show abstract

Section: Historical Overviewmentioning

confidence: 99%

Computer vision meets metaverse

Zakynthinou,

Kanakaris,

Vrochidou

et al. 2024

View full text Add to dashboard Cite

show abstract

“…Ref. [34] introduces Style Matching CAPTCHA (SMC) employing neural-style transfer (NST) to combine security and user-friendliness. SMC tasks users with recognizing the style used in stylization, promoting a balanced approach to thwart bot attacks, including deep learning models.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Based CAPTCHA Recognition Network with Grouping Strategy

Derea,

Zou,

Al-Shargabi

et al. 2023

Sensors

View full text Add to dashboard Cite

Websites can improve their security and protect against harmful Internet attacks by incorporating CAPTCHA verification, which assists in distinguishing between human users and robots. Among the various types of CAPTCHA, the most prevalent variant involves text-based challenges that are intentionally designed to be easily understandable by humans while presenting a difficulty for machines or robots in recognizing them. Nevertheless, due to significant advancements in deep learning, constructing convolutional neural network (CNN)-based models that possess the capability of effectively recognizing text-based CAPTCHAs has become considerably simpler. In this regard, we present a CAPTCHA recognition method that entails creating multiple duplicates of the original CAPTCHA images and generating separate binary images that encode the exact locations of each group of CAPTCHA characters. These replicated images are subsequently fed into a well-trained CNN, one after another, for obtaining the final output characters. The model possesses a straightforward architecture with a relatively small storage in system, eliminating the need for CAPTCHA segmentation into individual characters. Following the training and testing of the suggested CNN model for CAPTCHA recognition, the experimental results demonstrate the model’s effectiveness in accurately recognizing CAPTCHA characters.

show abstract

Style matching CAPTCHA: match neural transferred styles to thwart intelligent attacks

Abstract: Noname manuscript No.

Cited by 2 publications

References 86 publications

Computer vision meets metaverse

Computer vision meets metaverse

Deep Learning Based CAPTCHA Recognition Network with Grouping Strategy

Contact Info

Product

Resources

About