Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DMTG: A Human-Like Mouse Trajectory Generation Bot Based on Entropy-Controlled Diffusion Networks

Jiahua Liu, Zeyuan Cui, Wenhan Ge, Pengxiang Zhan

TL;DR

A diffusion model-based mouse trajectory generation framework (DMTG), which controls trajectory complexity and produces realistic human-like mouse movements and mimics physical human behaviors, demonstrating improved performance in both simulation and real-world CAPTCHA scenarios.

Abstract

CAPTCHAs protect against resource misuse and data theft by distinguishing human activity from automated bots. Advances in machine learning have made traditional image and text-based CAPTCHAs vulnerable to attacks, leading modern CAPTCHAs, such as GeeTest and Akamai, to incorporate behavioral analysis like mouse trajectory detection. Existing bypass techniques struggle to fully mimic human behavior, making it difficult to evaluate the effectiveness of anti-bot measures. To address this, we propose a diffusion model-based mouse trajectory generation framework (DMTG), which controls trajectory complexity and produces realistic human-like mouse movements. DMTG also provides white-box and black-box testing methods to assess its ability to bypass CAPTCHA systems. In experiments, DMTG reduces bot detection accuracy by 4.75%-9.73% compared to other models. Additionally, it mimics physical human behaviors, such as slow initiation and directional force differences, demonstrating improved performance in both simulation and real-world CAPTCHA scenarios.

DMTG: A Human-Like Mouse Trajectory Generation Bot Based on Entropy-Controlled Diffusion Networks

TL;DR

A diffusion model-based mouse trajectory generation framework (DMTG), which controls trajectory complexity and produces realistic human-like mouse movements and mimics physical human behaviors, demonstrating improved performance in both simulation and real-world CAPTCHA scenarios.

Abstract

CAPTCHAs protect against resource misuse and data theft by distinguishing human activity from automated bots. Advances in machine learning have made traditional image and text-based CAPTCHAs vulnerable to attacks, leading modern CAPTCHAs, such as GeeTest and Akamai, to incorporate behavioral analysis like mouse trajectory detection. Existing bypass techniques struggle to fully mimic human behavior, making it difficult to evaluate the effectiveness of anti-bot measures. To address this, we propose a diffusion model-based mouse trajectory generation framework (DMTG), which controls trajectory complexity and produces realistic human-like mouse movements. DMTG also provides white-box and black-box testing methods to assess its ability to bypass CAPTCHA systems. In experiments, DMTG reduces bot detection accuracy by 4.75%-9.73% compared to other models. Additionally, it mimics physical human behaviors, such as slow initiation and directional force differences, demonstrating improved performance in both simulation and real-world CAPTCHA scenarios.

Paper Structure

This paper contains 19 sections, 14 equations, 6 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. CAPTCHA and Deceivers
  4. Generative Artificial Intelligence
  5. Methodlogy
  6. Issue Definitions
  7. Data Collection
  8. Model Construction
  9. Mouse Trajectory Initialization
  10. $\alpha$-DDIM Framework
  11. $\alpha$-DDIM Losses
  12. Evaluation
  13. Simulation Confidence Assessments
  14. Commercial CAPTCHA Validations
  15. Experiments
  16. ...and 4 more sections

Figures (6)

  • Figure 1: DMTG Framework
  • Figure 2: Simulation Results of Points Num $m$, Info Entropy $H(\{p_a\})$, and MST Length $\log(\mathbb{E}(L_{MST}(\{p_a\})))$
  • Figure 3: U-Net Model for $\alpha$-DDIM
  • Figure 4: Examples of DMTG Curves under Different $\bm{\alpha}$ Values in \ref{['eq:style-emb']}
  • Figure 5: Difference in Acceleration between Upward and Downward Mouse Movements
  • ...and 1 more figures