Secure QR Code Scanner to Detect Malicious URL using Machine Learning

Pawar, Atharva; Fatnani, Chirag; Sonavane, Rajani; Waghmare, Riya; Saoji, Sarang

doi:10.1109/asiancon55314.2022.9908759

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, a comprehensive investigation was conducted by Shantanu et al [14] to assess the performance of seven machine learning classifiers in the detection of malicious URLs; the RF classifier demonstrated superior performance compared to the other classifiers, achieving an accuracy rate of 92.65%. Another study employed four machine learning classifiers to implement a secure QR code scanner to detect malicious URLs; the bidirectional Long Short-Term Memory (LSTM) classifier achieved the highest performance, with an accuracy rate of 83.79% [15]. Rafsanjani et al [16] proposed QsecR, an Android application designed to offer QR code scanning functionalities that prioritize security and privacy based on malicious URL detection.…”

Section: B Url-based Approachesmentioning

confidence: 99%

“…Ideally, both precision and recall should be maximized. More importantly, they should maintain a balance to indicate unbiased and wellrounded predictions [15].…”

Section: Recall = T P T P + Fnmentioning

confidence: 99%

“…Considering such threats, QR code attacks have become a critical concern, necessitating effective countermeasures to mitigate them and to preserve the security and integrity of QR codes. Many techniques have been proposed to safeguard QR codes from malicious embedded URLs, such as employing encryption techniques to protect the data embedded in QR codes [8], [9], [10], [11] or utilizing secure QR code generators and scanners that provide built-in malicious content detection capabilities [12], [13], [14], [15], [16]. This study aims to introduce and examine the efficacy of a dual machine learningbased model to recognize malicious URLs embedded in QR codes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

QR Shield: A Dual Machine Learning Approach Towards Securing QR Codes

Almousa,

Almarzoqi,

Alassaf

et al. 2024

IJCDS

View full text Add to dashboard Cite

Quick Response (QR) codes, extensively employed due to their compatibility with smartphone technology and the technological advances of QR code scanners, have become a crucial aspect of modern life. With the ever-increasing adoption and utilization of QR codes in various real-life contexts, finding effective and efficient security mechanisms to maintain their integrity has become paramount. Despite their popularity, QR codes have been exploited as potential attack vectors through which attackers encode malicious URLs. Such attacks have become a critical concern, necessitating effective countermeasures to mitigate them. In response to this pressing issue, this research paper introduces QR Shield, a dual machine learning-based model designed to address the security vulnerabilities inherent in QR codes. Following extensive testing of multiple machine learning algorithms, two of the most promising algorithms have been integrated into this model, namely the Random Forest (RF) and XGBoost algorithms. The QR Shield employs these sophisticated machine learning algorithms to accurately identify and detect malicious URLs embedded within QR codes, utilizing a benchmark dataset of URLs. Through rigorous evaluation using four key metrics, the effectiveness of the QR Shield is demonstrated, with experimental results showcasing an impressive accuracy rate of 96.8%. Based on these outcomes, the QR Shield exhibits a high potential to detect malicious URLs embedded within QR codes, which confirms the ability to generalize the proposed QR Shield to various real-life domains and applications. Additionally, the present study contributes significantly to the broader field of QR code security by offering comprehensive insights into the efficacy of supervised machine learning models in enhancing QR code security and privacy, thus paving the way for future advancements in this critical area of research.

show abstract

Section: B Url-based Approachesmentioning

confidence: 99%

“…Ideally, both precision and recall should be maximized. More importantly, they should maintain a balance to indicate unbiased and wellrounded predictions [15].…”

Section: Recall = T P T P + Fnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

QR Shield: A Dual Machine Learning Approach Towards Securing QR Codes

Almousa,

Almarzoqi,

Alassaf

et al. 2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…QR Code merupakan perkembangan dari barcode yang dikembangkan oleh denso wave. Perbedaan QR Code dan barcode terletak pada penyimpan data, barcode menyimpan data yang lebih pendek dibanding QR Code [6]. QR Code dapat dibuat dengan mudah, banyak website yang menyediakan tools mengubah angka, huruf dan simbol menjadi QR Code.…”

Section: Pendahuluanunclassified

Rancang bangun sistem pengaman rumah dengan aplikasi android berbasis motion detection dan QR code

Wirayoga,

Imammuddien,

Wahyuningsih

et al. 2023

eltek

View full text Add to dashboard Cite

Pada rumah yang terdapat di perkotaan sering kali terjadi pencurian barang atau kendaraan. Pada saat bepergian pemilik rumah akan merasa tidak aman jika meninggalkan rumah tanpa pengawasan. Alat yang dibuat pada penelitian ini bertujuan untuk membuat pengamanan rumah pada saat pemililik rumah sedang bepergian dan membuat alat untuk mengurangi tingkat pencurian terutama di daerah perkotaan. Pada prototype sistem keamanan rumah ini membutuhkan aplikasi android yang dirancang pada kodular, kodular merupakan layanan berbasis web yang digunakan dalam hal pemograman untuk merancang dan membuat suatu aplikasi android kemudian membutuhkan firebase untuk menyimpan data. Sensor PIR (Passive Infra Red) HC-SR501 yang digunakan pada alat ini dapat mendeteksi pergerakan seseorang dengan jarak maksimal 400 cm. Sensor proximity E18-D80NK yang digunakan pada alat ini dapat mendeteksi pergerakan objek dengan jarak maksimal 60 cm. ABSTRACTIn houses located in urban areas, theft of goods or vehicles is often the case. When traveling, homeowners will feel unsafe if they leave the house unattended. The tool made in this study aims to make home security when the homeowner is traveling and make tools to reduce the theft rate, especially in urban areas. The prototype of this home security system requires an android application designed on modular, modular is a web-based service that is used in programming to design and create an android application then requires firebase to store data. The HC-SR501 PIR (Passive Infra Red) sensor used in this tool can detect the movement of a person with a maximum distance of 400 cm. The E18-D80NK proximity sensor used in this tool can detect the movement of objects with a maximum distance of 60 cm.

show abstract