[[TOC(Other/Summer/2023/SecurityAI/*, depth=1, heading=Security in Aritificial Intelligence)]]

= Security in Artificial Intelligence =
**WINLAB Summer Internship 2023**

**Advisors:** Tianfang Zhang, Changming Li, Hong 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. Backdoor attacks originate from the image domain, and recent studies have started investigating audio-domain backdoor attacks (e.g., against voice assistant systems). This project aims to study the vulnerabilities of backdoor attacks in the image and audio domains and develop techniques for attack mitigation.

== Week 1 ==
**Summary**
* Established project objectives
* Covered and reviewed background information on topics (adversarial attacks, backdoor attacks, etc.)
* [https://www.orbit-lab.org/attachment/wiki/Other/Summer/2023/SecurityAI/1412.6572.pdf]
* Developed a plan of action for the upcoming weeks

[[Image({C52B7779-4CD1-40A3-9938-9711E34DFB86}.png)]]  [[Image({C5E828CF-69BF-4DB6-9960-6A1E754AC68B}.png​)]]

**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
**Summary**
* Familiarized ourselves with PyTorch  
* Stared researching papers about Smart User Authentication (WiFi-enabled IOT)
* Explored into attack mitigation
[[Image({038A11F1-8AFA-4FD5-ACAA-462CE34D7381}.png)]]  [[Image({30880812-ECF5-4090-B6C4-E00FFA0DF872}.png​)]]

**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
**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
[[Image(Screenshot 2023-07-06 110736.png)]]

**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
**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
[[Image(Screenshot 2023-07-06 110340.png)]]

**Resources**\\

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