Attacks on Machine Learning Models Based on the PyTorch Framework-Reference-Cited by-同舟云学术

Attacks on Machine Learning Models Based on the PyTorch Framework

Published:2024-03 Issue:3 Volume:85 Page:
ISSN:0005-1179
Container-title:Automation and Remote Control
language:
Short-container-title:ARC

Author:

,Namiot D. E.,Bidzhiev T. M.,

Abstract

This research delves into the cybersecurity implications of neural network training in cloud-based services. Despite their recognition for solving IT problems, the resource-intensive nature of neural network training poses challenges, leading to increased reliance on cloud services. However, this dependence introduces new cybersecurity risks. The study focuses on a novel attack method exploiting neural network weights to discreetly distribute hidden malware. It explores seven embedding methods and four trigger types for malware activation. Additionally, the paper introduces an open-source framework automating code injection into neural network weight parameters, allowing researchers to investigate and counteract this emerging attack vector.

Publisher

The Russian Academy of Sciences

Reference31 articles.

1. 1. Namiot, D., Ilyushin, E., Pilipenko, O., On Trusted AI Platforms, Int. J. Open Inform. Techn., 2022, vol. 10, no. 7, pp. 119-127.

2. 2. Kostyumov, V., A Survey and Systematization of Evasion Attacks in Computer Vision, Int. J. Open Inform. Techn., 2022, vol. 10, no. 10, pp. 11-20.

3. 3. Stoecklin, M.Ph., Jang, J., and Kirat, D., DeepLocker: How AI Can Power a Stealthy New Breed of Malware, Security Intelligence, 2018, vol. 8.

4. 4. Ilyushin, E., Namiot, D., and Chizhov, I., Attacks on Machine Learning Systems-Common Problems and Methods, Int. J. Open Inform. Techn., 2022, vol. 10, no. 3, pp. 17-22.

5. 5. Liu, T. et al., StegoNet: Turn Deep Neural Network into a Stegomalware, in Annual Computer Security Applications Conference. ACSAC'20, 2020, pp. 928-938.