Enhancing TinyML Security: Study of Adversarial Attack Transferability

TL;DR

This paper investigates the transferability of adversarial attacks in TinyML, revealing vulnerabilities in resource-constrained devices like ESP32 and Raspberry Pi, and emphasizing the need for improved security measures.

Contribution

It provides the first detailed analysis of how adversarial attacks transfer from powerful hosts to tiny embedded devices in TinyML environments.

Findings

Adversarial attacks can transfer from host to tiny devices.

TinyML devices are vulnerable to model extraction and evasion attacks.

Security measures are essential for safe TinyML deployment.

Abstract

The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data analysis and swift responses critical for diverse applications, its devices' intrinsic resource limitations expose them to security risks. This research delves into the adversarial vulnerabilities of AI models on resource-constrained embedded hardware, with a focus on Model Extraction and Evasion Attacks. Our findings reveal that adversarial attacks from powerful host machines could be transferred to smaller, less secure devices like ESP32 and Raspberry Pi. This illustrates that adversarial attacks could be extended to tiny devices, underscoring vulnerabilities, and emphasizing the necessity for reinforced security measures in TinyML deployments. This exploration enhances the comprehension of security challenges in TinyML and offers insights for safeguarding sensitive data and ensuring device dependability in AI-powered edge computing settings.