Crypto Miner Attack: GPU Remote Code Execution Attacks

TL;DR

This paper investigates GPU-based remote code execution attacks that exploit deserialization vulnerabilities and custom layers in AI systems to deploy malicious crypto miners, highlighting detection challenges and mitigation strategies.

Contribution

It provides a comprehensive analysis of GPU RCE exploits, demonstrating how they can be used to deploy crypto miners and proposing mitigation strategies.

Findings

GPU RCE attacks enable unauthorized crypto mining.

Detection of GPU-based attacks is highly challenging due to parallel processing.

Static and model scanning can help mitigate these vulnerabilities.

Abstract

Remote Code Execution (RCE) exploits pose a significant threat to AI and ML systems, particularly in GPU-accelerated environments where the computational power of GPUs can be misused for malicious purposes. This paper focuses on RCE attacks leveraging deserialization vulnerabilities and custom layers, such as TensorFlow Lambda layers, which are often overlooked due to the complexity of monitoring GPU workloads. These vulnerabilities enable attackers to execute arbitrary code, blending malicious activity seamlessly into expected model behavior and exploiting GPUs for unauthorized tasks such as cryptocurrency mining. Unlike traditional CPU-based attacks, the parallel processing nature of GPUs and their high resource utilization make runtime detection exceptionally challenging. In this work, we provide a comprehensive examination of RCE exploits targeting GPUs, demonstrating an attack that utilizes these vulnerabilities to deploy a crypto miner on a GPU. We highlight the technical intricacies of such attacks, emphasize their potential for significant financial and computational costs, and propose strategies for mitigation. By shedding light on this underexplored attack vector, we aim to raise awareness and encourage the adoption of robust security measures in GPU-driven AI and ML systems, with an emphasis on static and model scanning as an easier way to detect exploits.