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

• URL: http://arxiv.org/abs/2605.09431v1
• Date: Sun, 10 May 2026 09:10:13 GMT
• Title: PumpSense: Real-Time Detection and Target Extraction of Crypto Pump-and-Dumps on Telegram
• Abstract summary: We introduce a corpus of over 280,000 Telegram posts from 39 pump-organizing groups.<n>We define two tasks: real-time pump-announcement detection and target cryptocurrency/exchange extraction.<n>We show that message analysis can achieve near-instant pump detection at the level of individual Telegram message windows.
• Score: 2.4493299476776778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Don't You Know, Pump it Up! Investigating Cryptocurrency Manipulation in Telegram-Driven Activity [0.6299766708197883]
  This work analyzes the interplay between information flows and market activity across public Telegram channels.<n>We apply this framework to one year of public Telegram data aligned with transaction data for more than 17,000 cryptocurrencies.<n>Our analysis identifies 47 events consistent with potential pump-and-dump activity and 73 sustained market reactions.
  arXiv  Detail & Related papers  (2026-09-01T12:51:41Z)
• \textsc{Perseus}: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes [7.268897486191816]
  Masterminds are entities organizing, coordinating, and orchestrating cryptocurrency pump-and-dump schemes.<n>Previous research detects pump-and-dump activities in the market, predicts the target cryptocurrency, and examines investors and acosn entities.<n>We develop a detection system textscPerseus, which collects real-time data from the acsosn and cryptocurrency markets.
  arXiv  Detail & Related papers  (2025-03-03T15:59:40Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification is a key element of machine learning applications.<n>We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines.<n>We conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs [16.25273745598176]
  Rise in cryptocurrency-related illicit activities has led to significant losses for users. Current detection methods mainly depend on feature engineering or are inadequate to leverage the complex information within cryptocurrency transaction networks. We present DIAM, an effective method for detecting illicit accounts in cryptocurrency transaction networks modeled by directed multi-graphs with attributed edges.
  arXiv  Detail & Related papers  (2023-09-04T09:01:56Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• Blockchain Large Language Models [65.7726590159576]
  This paper presents a dynamic, real-time approach to detecting anomalous blockchain transactions. The proposed tool, BlockGPT, generates tracing representations of blockchain activity and trains from scratch a large language model to act as a real-time Intrusion Detection System.
  arXiv  Detail & Related papers  (2023-04-25T11:56:18Z)
• Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump [39.06710188537909]
  This paper focuses on predicting the pump probability of all coins listed in the target exchange before a scheduled pump time. We conduct a comprehensive study of the latest 709 P&D events organized in Telegram from Jan. 2019 to Jan. 2022. We develop a novel sequence-based neural network, dubbed SNN, which encodes a channel's P&D event history into a sequence representation.
  arXiv  Detail & Related papers  (2022-04-21T16:34:53Z)
• The Doge of Wall Street: Analysis and Detection of Pump and Dump Cryptocurrency Manipulations [50.521292491613224]
  This paper performs an in-depth analysis of two market manipulations organized by communities over the Internet: The pump and dump and the crowd pump. The pump and dump scheme is a fraud as old as the stock market. Now, it got new vitality in the loosely regulated market of cryptocurrencies. We report on three case studies related to pump and dump groups.
  arXiv  Detail & Related papers  (2021-05-03T10:20:47Z)
• Pump and Dumps in the Bitcoin Era: Real Time Detection of Cryptocurrency Market Manipulations [50.521292491613224]
  We perform an in-depth analysis of pump and dump schemes organized by communities over the Internet. We observe how these communities are organized and how they carry out the fraud. We introduce an approach to detect the fraud in real time that outperforms the current state of the art.
  arXiv  Detail & Related papers  (2020-05-04T21:36:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.