PumpSense: Real-Time Detection and Target Extraction of Crypto Pump-and-Dumps on Telegram

TL;DR

This paper presents PumpSense, a real-time Telegram message analysis system for detecting and extracting crypto pump-and-dump schemes, achieving high accuracy and low latency with a new labeled dataset.

Contribution

It introduces a large, manually labeled Telegram dataset and compares machine learning models for instant pump detection and target extraction, establishing new benchmarks.

Findings

LightGBM achieves F1=0.79 with 9.4 s latency.

BGE-M3 transformer achieves F1=0.83 with 50 ms latency.

LLMs outperform rule-based methods with 0.91 accuracy.

Abstract

Cryptocurrency pump-and-dump schemes coordinated via Telegram threaten market integrity. However, existing research addressing this specific threat has not yet produced solutions that combine reliable results with fast response. This is in part due to the absence of publicly available, message-level labeled data, as well as design choices. In this paper, we address both issues. In particular, we introduce a corpus of over 280,000 Telegram posts from 39 pump-organizing groups, all manually reviewed to identify 2,246 pump announcements and their targeted cryptocurrency and exchange. Leveraging this dataset, we define two tasks: real-time pump-announcement detection and target cryptocurrency/exchange extraction. For detection, we compare two machine-learning models: a lightweight tree-based LightGBM classifier (F1=0.79, latency=9.4 s/sample) and a transformer-based BGE-M3 (F1=0.83, latency=50 ms/sample). With our proposed approach, we show that message analysis can achieve near-instant pump detection at the level of individual Telegram message windows. Unlike prior work that relies purely on market data and typically detects pumps tens of seconds after abnormal trading activity is observed, our method operates directly on the coordination messages themselves and can be evaluated in microseconds per window on commodity hardware. To our knowledge, we also establish the first benchmark for manipulated coin and exchange extraction. We demonstrate that traditional rule-based extraction methods, widely relied upon in prior literature, are ineffective due to ticker ambiguity. In contrast, LLMs achieve the highest accuracy with a score of 0.91.