# POSTER: A Multi-Signal Model for Detecting Evasive Smishing

arXiv: https://arxiv.org/abs/2505.18233 · HTML: https://mlsanity.com/paper/2505.18233/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 2 of 2)

- [Smishing Dataset I: Phishing SMS Dataset from Smishtank.com](https://mlsanity.com/paper/2402.18430/) (2024)
- [SpaLLM-Guard: Pairing SMS Spam Detection Using Open-source and Commercial LLMs](https://mlsanity.com/paper/2501.04985/) (2025)

## Built on by (most cited first, 1 of 1)

- [ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification](https://mlsanity.com/paper/2609.04878/) (2026)

## Abstract (arXiv)

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.