Security in Artificial Intelligence

WINLAB Summer Internship 2023

Advisors: Yingying Chen, Tianfang Zhang, Changming Li, Honglu Li

Group Members: Rut Mehta, Jacob Morin, Ethan Lung, Damon Lin

Project Objective

Artificial intelligence techniques have been widely integrated into mobile and IoT devices, enabling various functionalities based on vision (e.g., face recognition, speech recognition, and speaker identification). The extended pipeline of building deep neural networks (DNN) produces new attack surfaces, such as attacks during the data collection, model training, and model update stages. Recent research studies discovered an effective yet stealthy attack, called a backdoor attack, which trains a hidden trigger pattern into the DNNs. The backdoored DNNs will misclassify an input as an adversary-specified label if the trigger pattern appears, behaving normally otherwise, making it difficult to be detected. This project focuses on improving the security behind user authentication through conventional means (e.g., passwords and facial detection) by replacing it with a biometric signature in the form of daily activities. Following this implementation, the project aims to study the vulnerabilities of backdoor attacks on such a system and develop techniques for attack mitigation.

Week 1

​Week 1 Presentation

Summary

• Established project objectives
• Covered and reviewed background information on topics (adversarial attacks, backdoor attacks, etc.)
  • ​https://acrobat.adobe.com/id/urn:aaid:sc:US:abef282d-0f73-4532-8339-23a159f6977f
• Developed a plan of action for the upcoming weeks

Resources

​https://venturebeat.com/security/adversarial-attacks-in-machine-learning-what-they-are-and-how-to-stop-them/

​https://www.engati.com/blog/ai-for-cybersecurity#:~:text=AI%20in%20cybersecurity%20eliminates%20time,on%20more%20critical%20security%20tasks.

Week 2

​Week 2 Presentation

Summary

• Familiarized ourselves with PyTorch
• Started researching papers about Smart User Authentication (WiFi-enabled IOT)
• Explored attack mitigation

Resources

​https://pytorch.org/tutorials/beginner/basics/intro.html

​https://www.hypr.com/security-encyclopedia/iot-authentication#:~:text=IoT%20(Internet%20of%20Things)%20Authentication,%2C%20transportation%20hubs%2C%20and%20workplaces

Week 3

​Week 3 Presentation

Summary

• Continued learning advanced PyTorch functions for IoT interference data.
• Set up experiments to collect interference data from mobile devices
• Examined Channel State Information (CSI) Amplitudes

Resources

​http://tns.thss.tsinghua.edu.cn/wst/docs/pre/

​https://www.mdpi.com/1099-4300/23/9/1164#:~:text=The%20physical%20meaning%20of%20CSI,fading%20%5B26%2C27%5D

Week 4

​Week 4 Presentation

Summary

• Set up Linux virtual machine through VirtualBox (Ubuntu)
• Familiarized ourselves with Linux Terminal
• Installed Nexmon (Channel State Information tool, Extract CSI from phone)
• Used Android Phones (Nexus 5 & Nexus 6) to perform experiments

Resources

​https://github.com/seemoo-lab/nexmon_csi#getting-started

Week 5

​Week 5 Presentation

Summary

• Installed custom ROMs on both the Nexus 5 and Nexus 6
• Resolved Nexus 5 WiFi bug
• Installed suggested Android version for Nexus 6

Week 6

​Week 6 Presentation

Summary *

Week 7

​Week 7 Presentation

Summary *

Week 8

​Week 8 Presentation (skipped)

Summary

• Configured one Nexus 5 as a receiver for Wi-Fi packets
  • Setup an experiment with this phone and router

• Met with one of our mentors and received sample CSI data + more guidance on experimentation
• Received functioning Nexus 5 from Professor Chen
  • Working on configuring this phone as a transmitter
• Participated in an experiment conducted by one of our mentors

Week 9

[insert presentation link]

Summary

• Completed participation in mentor's experiment
• Designing final poster

Week 10