POSTER: A Multi-Signal Model for Detecting Evasive Smishing
This work addresses the threat of smishing for mobile users by improving detection accuracy, though it appears incremental as it builds on existing multi-signal approaches.
The paper tackled the problem of detecting SMS-based phishing (smishing) by developing a multi-channel model that combines semantic, structural, stylistic, and contextual features, achieving 97.89% accuracy, an F1 score of 0.963, and an AUC of 99.73% on a dataset of over 84,000 messages.
Smishing, or SMS-based phishing, poses an increasing threat to mobile users by mimicking legitimate communications through culturally adapted, concise, and deceptive messages, which can result in the loss of sensitive data or financial resources. In such, we present a multi-channel smishing detection model that combines country-specific semantic tagging, structural pattern tagging, character-level stylistic cues, and contextual phrase embeddings. We curated and relabeled over 84,000 messages across five datasets, including 24,086 smishing samples. Our unified architecture achieves 97.89% accuracy, an F1 score of 0.963, and an AUC of 99.73%, outperforming single-stream models by capturing diverse linguistic and structural cues. This work demonstrates the effectiveness of multi-signal learning in robust and region-aware phishing.