Abstract:
When people use social networks, they often fall prey to a clickbait scam. The scammer
attempts to create a striking headline that attracts the majority of users and attaches a link. The user
follows the link and can be redirected to a fraudulent resource where the user easily loses personal
data. To solve this problem, a Blockchain-enabled deep recurrent neural network (BDRNN) is proposed
to detect the nature safe and malicious clickbait from the contents. The proposed BDRNN consists of
three phases: analysis of clickbait and source rating, clickbait search process and multi-layered clickbait
detection. The analysis of clickbait and source rating phase helps to analyze different sources to detect
the clickbait and also rating the content-sources. To achieve the clickbait analysis and source rating, the
detection of blocklisted/allowlisted source and source rating check algorithms are introduced. The clickbait
search process is accomplished by incorporating the binary search features for a faster and more efficient
search process for malicious content-detection. The multi-layered clickbait detection is main phase of
the proposed BDRNN that consists of three models: content-to-vector model (layer-1), deep neural
network model(layer-2), and Blockchain-enabled malicious content detection model (layer-3). These models
collectively detect the malicious and safe clickbait from the contents. The extensive experiments are
conducted to determine the effectiveness of the proposed BDRNN model and compared with the existing
state-of-the-art neural network models designed for clickbait detection, and the result demonstrates that the
proposed BDRNN model outperforms the counterparts from the, accuracy, link detection, memory usage,
analogous perspectives, and attacker’s successful content capturing rate.
