Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Detection of Illicit Content on Online Marketplaces using Large Language Models

Quoc Khoa Tran, Thanh Thi Nguyen, Campbell Wilson

TL;DR

This research investigates the efficacy of Large Language Models, specifically Meta's Llama 3.2 and Google's Gemma 3, in detecting and classifying illicit online marketplace content using the multilingual DUTA10K dataset and reveals a task-dependent advantage for LLMs.

Abstract

Online marketplaces, while revolutionizing global commerce, have inadvertently facilitated the proliferation of illicit activities, including drug trafficking, counterfeit sales, and cybercrimes. Traditional content moderation methods such as manual reviews and rule-based automated systems struggle with scalability, dynamic obfuscation techniques, and multilingual content. Conventional machine learning models, though effective in simpler contexts, often falter when confronting the semantic complexities and linguistic nuances characteristic of illicit marketplace communications. This research investigates the efficacy of Large Language Models (LLMs), specifically Meta's Llama 3.2 and Google's Gemma 3, in detecting and classifying illicit online marketplace content using the multilingual DUTA10K dataset. Employing fine-tuning techniques such as Parameter-Efficient Fine-Tuning (PEFT) and quantization, these models were systematically benchmarked against a foundational transformer-based model (BERT) and traditional machine learning baselines (Support Vector Machines and Naive Bayes). Experimental results reveal a task-dependent advantage for LLMs. In binary classification (illicit vs. non-illicit), Llama 3.2 demonstrated performance comparable to traditional methods. However, for complex, imbalanced multi-class classification involving 40 specific illicit categories, Llama 3.2 significantly surpassed all baseline models. These findings offer substantial practical implications for enhancing online safety, equipping law enforcement agencies, e-commerce platforms, and cybersecurity specialists with more effective, scalable, and adaptive tools for illicit content detection and moderation.

Detection of Illicit Content on Online Marketplaces using Large Language Models

TL;DR

This research investigates the efficacy of Large Language Models, specifically Meta's Llama 3.2 and Google's Gemma 3, in detecting and classifying illicit online marketplace content using the multilingual DUTA10K dataset and reveals a task-dependent advantage for LLMs.

Abstract

Online marketplaces, while revolutionizing global commerce, have inadvertently facilitated the proliferation of illicit activities, including drug trafficking, counterfeit sales, and cybercrimes. Traditional content moderation methods such as manual reviews and rule-based automated systems struggle with scalability, dynamic obfuscation techniques, and multilingual content. Conventional machine learning models, though effective in simpler contexts, often falter when confronting the semantic complexities and linguistic nuances characteristic of illicit marketplace communications. This research investigates the efficacy of Large Language Models (LLMs), specifically Meta's Llama 3.2 and Google's Gemma 3, in detecting and classifying illicit online marketplace content using the multilingual DUTA10K dataset. Employing fine-tuning techniques such as Parameter-Efficient Fine-Tuning (PEFT) and quantization, these models were systematically benchmarked against a foundational transformer-based model (BERT) and traditional machine learning baselines (Support Vector Machines and Naive Bayes). Experimental results reveal a task-dependent advantage for LLMs. In binary classification (illicit vs. non-illicit), Llama 3.2 demonstrated performance comparable to traditional methods. However, for complex, imbalanced multi-class classification involving 40 specific illicit categories, Llama 3.2 significantly surpassed all baseline models. These findings offer substantial practical implications for enhancing online safety, equipping law enforcement agencies, e-commerce platforms, and cybersecurity specialists with more effective, scalable, and adaptive tools for illicit content detection and moderation.
Paper Structure (34 sections, 3 figures, 3 tables)

This paper contains 34 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Supervised Learning Approaches
  4. Unsupervised Learning Approaches
  5. Deep Learning Techniques
  6. Transformer-Based Models
  7. Large Language Models (LLMs)
  8. Research Gaps
  9. Methodology
  10. Research Design Overview
  11. Investigated Dataset
  12. Dataset Curation and Characteristics
  13. Ethical Considerations
  14. Preprocessing
  15. Experimental Setup and Models
  16. ...and 19 more sections

Figures (3)

  • Figure 1: Top 10 Main Categories in the DUTA10K Dataset.
  • Figure 2: Llama and Gemma training pipeline for text classification.
  • Figure 3: LLM structure in binary and multi-class text classification tasks.