College

College of Engineering and Polymer Science

Date of Last Revision

2026-05-06 06:30:05

Major

Computer Information Systems

Honors Course

CISS 491-001

Number of Credits

3

Degree Name

<-- Please Select One -->

Date of Expected Graduation

Spring 2026

Abstract

Alert fatigue occurs during long hour shifts and high stress situations. Constant notifications and on-call shifts can create overstimulation and desensitization, which leads to delay responses and increased vulnerability. Malicious actors have weaponized alert fatigue by storming a network with a vast number of low-priority events to mask their malicious activity, also known as alert storming. This project focuses on the reduction of alert fatigue by automating log analysis with Large Language Models. The project uses Amazon Web Service and its many features, such as Amazon GuardDuty, Lambda, and Bedrock. Amazon GuardDuty detects anomalies, then lambda sends those anomalies to Amazon Bedrock for further analysis. Amazon Bedrock will provide a summary of the problem and how to remediate the problem. The project will be deployable for smaller security teams and alert them of an anomaly in seconds while not requiring any hardware.

Research Sponsor

Nadhem Ebrahim

First Reader

Stanley Smith

Second Reader

Tiffany McClaskey

Honors Faculty Advisor

Janet Kropff

Proprietary and/or Confidential Information

No

Community Engaged Scholarship

No

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.