Haptic-Based User Authentication for Tele-robotic System

2025-06-17

AI Summary

To address the vulnerability of conventional cryptographic and static biometric authentication to replay and spoofing attacks in teleoperated robotic systems, this paper proposes a continuous authentication method leveraging dynamic haptic feedback. The approach uniquely exploits real-time, task-embedded force-tactile time-series signals generated naturally during human–robot interaction to establish a lightweight, replay-resistant, and spoof-proof behavioral authentication mechanism. Force data were collected from 15 participants performing seven distinct teleoperation tasks, and a dedicated Transformer-based architecture was designed to extract highly discriminative temporal features. Experimental results demonstrate that the proposed method achieves over 90% accuracy in both user identification and task classification—significantly enhancing real-time identity assurance and security in high-risk, prolonged human–robot interaction scenarios.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

Tele-operated robots rely on real-time user behavior mapping for remote tasks, but ensuring secure authentication remains a challenge. Traditional methods, such as passwords and static biometrics, are vulnerable to spoofing and replay attacks, particularly in high-stakes, continuous interactions. This paper presents a novel anti-spoofing and anti-replay authentication approach that leverages distinctive user behavioral features extracted from haptic feedback during human-robot interactions. To evaluate our authentication approach, we collected a time-series force feedback dataset from 15 participants performing seven distinct tasks. We then developed a transformer-based deep learning model to extract temporal features from the haptic signals. By analyzing user-specific force dynamics, our method achieves over 90 percent accuracy in both user identification and task classification, demonstrating its potential for enhancing access control and identity assurance in tele-robotic systems.

Problem

• Secure authentication in tele-robotic systems
• Vulnerability of traditional methods to attacks
• Behavioral feature extraction from haptic feedback

Innovation

• Haptic feedback for user authentication
• Transformer-based deep learning model
• Analyzes user-specific force dynamics