Chat or Trap? Detecting Scams in Messaging Applications with Large Language Models
Bibliographic record
Abstract
Messaging applications have become integral to everyday communication, but their widespread use has also made them a hotbed of various scams. Cybercriminals exploit these platforms, using sophisticated social engineering techniques to deceive individuals, build trust and achieve financial gain. The advent of Generative Artificial Intelligence (GenAI) has further exacerbated the problem of scams, enabling the creation of more sophisticated and convincing fraudulent schemes. Much research has focused on detecting phishing emails and spam messages, overlooking scenarios where malicious actors initiate conversations in a way that appears harmless. This paper proposes leveraging Large Language Models (LLMs) to detect scams in chats on messaging applications. A comprehensive dataset comprising real-world scam and non-scam chat segments is constructed, followed by a thorough performance comparison of various LLMs in identifying scam indicators within chat segments. Additionally, a comparative analysis is performed between LLMs and human participants in recognizing these deceptive interactions through a detailed survey. The findings highlight the potential of LLMs to mitigate the growing threat of scams in messaging applications, thereby enhancing the security of digital communications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".