homepage
Menu
Open menu
  • Training
    Go one level top Back

    Training

    • Courses

      Build cyber prowess with training from renowned experts

    • Hands-On Simulations

      Hands-on learning exercises keep you at the top of your cyber game

    • Certifications

      Demonstrate cybersecurity expertise with GIAC certifications

    • Ways to Train

      Multiple training options to best fit your schedule and preferred learning style

    • Training Events & Summits

      Expert-led training at locations around the world

    • Free Training Events

      Upcoming workshops, webinars and local events

    • Security Awareness

      Harden enterprise security with end-user and role-based training

    Featured

    Get a Free Hour of SANS Training

    Free Course Demos

    Can't find what you are looking for?

    Let us help.
    Contact us
  • Learning Paths
    Go one level top Back

    Learning Paths

    • By Focus Area

      Chart your path to job-specific training courses

    • By NICE Framework

      Navigate cybersecurity training through NICE framework roles

    • DoDD 8140 Work Roles

      US DoD 8140 Directive Frameworks

    • By European Skills Framework

      Align your enterprise cyber skills with ECSF profiles

    • By Skills Roadmap

      Find the right training path based on critical skills

    • New to Cyber

      Give your cybersecurity career the right foundation for success

    • Leadership

      Training designed to help security leaders reduce organizational risk

    • Degree and Certificate Programs

      Gain the skills, certifications, and confidence to launch or advance your cybersecurity career.

    Featured: Solutions for Emerging Risks

    New to Cyber resources

    Start your career
  • Community Resources
    Go one level top Back

    Community Resources

    Watch & Listen

    • Webinars
    • Live Streams
    • Podcasts

    Read

    • Blog
    • Newsletters
    • White Papers
    • Internet Storm Center

    Download

    • Open Source Tools
    • Posters & Cheat Sheets
    • Policy Templates
    • Summit Presentations
    • SANS Community Benefits

      Connect, learn, and share with other cybersecurity professionals

    • CISO Network

      Engage, challenge, and network with fellow CISOs in this exclusive community of security leaders

  • For Organizations
    Go one level top Back

    For Organizations

    Team Development

    • Why Partner with SANS
    • Group Purchasing
    • Skills & Talent Assessments
    • Private & Custom Training

    Leadership Development

    • Leadership Courses & Accreditation
    • Executive Cybersecurity Exercises
    • CISO Network

    Security Awareness

    • End-User Training
    • Phishing Simulation
    • Specialized Role-Based Training
    • Risk Assessments
    • Public Sector Partnerships

      Explore industry-specific programming and customized training solutions

    • Sponsorship Opportunities

      Sponsor a SANS event or research paper

    Interested in developing a training plan to fit your organization’s needs?

    We're here to help.
    Contact us
  • Talk with an expert
  • Log In
  • Join - it's free
  • Account
    • Account Dashboard
    • Log Out
  1. Home >
  2. Blog >
  3. Leveraging Artificial Intelligence (AI) to Manage Human Risk: Part 6 – Analyzing Documents, Charts, and Spreadsheets
370x370_Lance-Spitzner.jpg
Lance Spitzner

Leveraging Artificial Intelligence (AI) to Manage Human Risk: Part 6 – Analyzing Documents, Charts, and Spreadsheets

AI can not only create resources, but also analyze many forms of data

December 7, 2023

Note: This blog post is the sixth in a series on AI and how to make the most of it in your Security Awareness, Culture, and Human Risk efforts. This post covers how to leverage AI to analyze various resources such as photos, diagrams, spreadsheets, and documents. You can access the other blog posts from this series below.

  • Part 1: Overview of AI
  • Part 2: Generative AI & Prompt Engineering
  • Part 3: Issues, Challenges, and Limitations of AI
  • Part 4: Advanced Prompt Engineering
  • Part 5: Generating Images
  • Part 6: Analyzing Data

Analyzing Data

Up to now we have focused on Generative AI’s ability to create resources, such as videos scripts, newsletter content, translations, generating customized images, and developing learning objectives for training. However, a feature just as powerful if not more powerful is its ability to analyze just about anything you give it. You can upload spreadsheets, word documents, graphs, photos, and diagrams, and it can not only comprehend but then analyze the material, giving you the ability to then improve the content, summarize it, or dive deeper into its meaning. A blog post like this can only begin to scratch the surface of just how powerful this feature is.

The first step is realizing you can pretty much upload anything you want to AI, and it will analyze it like a subject matter expert. Upload a financial document and AI can help you understand it like a Chief Financial Officer. Upload a flow diagram of a proposed application and it can analyze it like a Senior Software Developer. Upload a chart of your home’s energy usage and it can analyze it for you as if you are talking to the Department of Energy. These capabilities are almost frightening! Note, for the purpose of this blog I’m using OpenAI’s ChatGPT.

Now, before we proceed, a word of caution on privacy and security. Keep in mind that most AI solutions are public. This means anything you upload to the AI solution will not only be analyzed, but it will also remember and train itself on that file. This means your information can potentially be shared with others in the future. In some cases, the actual files you upload can be retrieved by others in their original format. This means you should never upload or share anything highly sensitive or confidential. If you want to use AI to analyze sensitive data, instead of using publicly available AI, use a private or enterprise version. This will protect and isolate any information you upload, ensuring that it is never used to train the AI and is not accessible or shared with others. Another option is to anonymize anything you upload.

So, what Can I Upload and Analyze?

This answer is any file you want. I’ll provide some examples in this blog post, but you can literally try virtually any file in any format. If it does not work now, try again next month, as AI is advancing rapidly. Here are just several of my favorite examples.

Screenshots

This is one of the most surprising capabilities of AI. You can upload a screenshot of almost anything visual (diagrams, charts, dashboards). For example, I uploaded the screenshot of a slide from the SANS LDR433 Human Risk course, then simply gave ChatGPT the prompt “explain what this slide means” with no other context.

The purpose of the slide is to visually compare just how much we the security community have invested in securing technology vs. securing employees. We do this by visualizing all the different security controls implemented over the past twenty years for the Windows Operating System vs. what the typical security team has done to help secure their workforce (i.e., very little) which we call the Human Operating System. Ever wonder why people are the primary attack vector? Because we have hit the point of diminishing returns by overinvesting in technology and underinvesting in securing people.

What really impressed me is when I uploaded the file, not only did the AI quickly pick up on the diagram’s intent and explain its meaning to me, but it also read, identified, and explained in more depth each of the technical controls listed in the order provided. If I wanted, I could then go in deeper and have AI explain in more detail each of the technical controls. Have a phone or electric bill you don’t understand? Take a screenshot of the part you are confused about, upload it, and have AI walk through the bill with you. Have a child struggling with their biology homework and don’t fully understand the diagram of a cell? Upload a screenshot and you now have your own subject matter expert that can explain it to your child in detail in a simple language that they can understand.

SSA_AI_Human_Risk_Blog_6_in_blog_graphic.png

Word Documents

AI can read and analyze just about any text-based document you give it (MS Word Document, PDF, etc.). I find the two biggest benefits for this to be the ability for AI to review a document and provide feedback on how to improve it or summarize it for me. Examples of improving a document include:

  • Simplifying security policies so they are easier to understand and follow,
  • Shortening your business case so you more effectively engage leadership,
  • Improving quiz questions based on a video script,
  • Modifying an email to your workforce so it focuses more on how they benefit from the new security tool being rolled out,
  • Suggesting titles for your new blog post, and
  • So many more!

Not only can AI provide recommendations on how to improve the wording, it can also increase (or decrease) the grade level at which the document was written, translate the content into another language, or rewrite the wording in a new voice, e.g., “rewrite the document but act like Shakespeare.”

Another powerful feature is AI’s ability to summarize. Perhaps there is a fascinating report on a security breach you want to read about, or a new analysis of the latest in cyber threat actor tactics and techniques, but you simply don’t have time to read the entire document. Or perhaps the document is too technical, and you just want to understand the key points. Provide AI the document (or the link to the document) and it will summarize it for you. It will also summarize a video. If there is a long video on YouTube you want to learn from, but the video is too long, download the transcript from the video, paste the transcript into AI, and have it summarize it for you.

Spreadsheets

Hate analyzing numbers? Having a hard time figuring out what that spreadsheet means or why the numbers don’t add up? I do all the time. With AI you can have your own personal Chief Financial Officer or Data Scientist do all the work for you. In most cases you can upload the spreadsheet with little to no context, as long as the columns and/or rows are somehow named or described. AI will analyze the spreadsheet and then explain its purpose and what each row or column represents. Then you can begin to ask it questions based on the data, such as the average costs per month or the percentage of increase/decrease over time. It can also help you find anomalies, such as which phishing simulation had the greatest click rates, or which department had the highest phishing simulation report rates.

Photos

This one is pretty simple, just upload a picture (any picture) and AI will explain what is happening in the picture. This may sound silly at first, but it can be quite useful. Let’s say you need to replace a part in your car or bike, but you have no idea what the part is called. Upload a picture of it and AI can analyze the image and the part for you. In addition, AI can explain how to replace the part and the tools you will most likely need. Or perhaps there is an amazing cake you would like to make, but you only have a picture of it. Upload the picture of the cake and AI can generate the recipe to make it. Or perhaps you have a picture of a car you like or a plant you would like to grow, but you don’t know the name of it, AI to the rescue! In addition, AI can decode and translate any text in the image, such as a poster written in a foreign language in the background of the picture. Features like these can also be useful for Open-Source Intelligence (OSINT) analysis of images.

Summary

We are literally just scratching the surface of what AI can analyze. If you can upload it, AI can handle it. What I’m looking forward to trying out is using AI to analyze future surveys. One of the traditional challenges of using surveys is asking open ended questions. It is extremely difficult to normalize, analyze, and categorize thousands of different responses from thousands of different people, (this is why surveys traditionally use the Likert 1-5 rating scale). With AI, we may be able to ask more open-ended questions and gain far richer data sets and insights into what we want to understand, like with the annual SANS Security Awareness Report.

With all that said, the best way to learn is to try. Remember, you cannot offend or wear out AI. It is happy to try its best to answer any request you send, as many times as you send. And again, be sure you are aware of the sensitivity of the files you upload. For sensitive files, either don’t upload them, sanitize them, or use private/enterprise AI solutions designed to protect the privacy of your data.

Interested in reducing your organization’s human risk? Check out my course LDR521: Security Culture for Leaders and sign up for a FREE course preview here.

Share:
TwitterLinkedInFacebook
Copy url Url was copied to clipboard
Subscribe to SANS Newsletters
Receive curated news, vulnerabilities, & security awareness tips
United States
Canada
United Kingdom
Spain
Belgium
Denmark
Norway
Netherlands
Australia
India
Japan
Singapore
Afghanistan
Aland Islands
Albania
Algeria
American Samoa
Andorra
Angola
Anguilla
Antarctica
Antigua and Barbuda
Argentina
Armenia
Aruba
Austria
Azerbaijan
Bahamas
Bahrain
Bangladesh
Barbados
Belarus
Belize
Benin
Bermuda
Bhutan
Bolivia
Bonaire, Sint Eustatius, and Saba
Bosnia And Herzegovina
Botswana
Bouvet Island
Brazil
British Indian Ocean Territory
Brunei Darussalam
Bulgaria
Burkina Faso
Burundi
Cambodia
Cameroon
Cape Verde
Cayman Islands
Central African Republic
Chad
Chile
China
Christmas Island
Cocos (Keeling) Islands
Colombia
Comoros
Cook Islands
Costa Rica
Cote D'ivoire
Croatia (Local Name: Hrvatska)
Curacao
Cyprus
Czech Republic
Democratic Republic of the Congo
Djibouti
Dominica
Dominican Republic
East Timor
Ecuador
Egypt
El Salvador
Equatorial Guinea
Eritrea
Estonia
Eswatini
Ethiopia
Falkland Islands (Malvinas)
Faroe Islands
Fiji
Finland
France
French Guiana
French Polynesia
French Southern Territories
Gabon
Gambia
Georgia
Germany
Ghana
Gibraltar
Greece
Greenland
Grenada
Guadeloupe
Guam
Guatemala
Guernsey
Guinea
Guinea-Bissau
Guyana
Haiti
Heard And McDonald Islands
Honduras
Hong Kong
Hungary
Iceland
Indonesia
Iraq
Ireland
Isle of Man
Israel
Italy
Jamaica
Jersey
Jordan
Kazakhstan
Kenya
Kiribati
Korea, Republic Of
Kosovo
Kuwait
Kyrgyzstan
Lao People's Democratic Republic
Latvia
Lebanon
Lesotho
Liberia
Liechtenstein
Lithuania
Luxembourg
Macau
Madagascar
Malawi
Malaysia
Maldives
Mali
Malta
Marshall Islands
Martinique
Mauritania
Mauritius
Mayotte
Mexico
Micronesia, Federated States Of
Moldova, Republic Of
Monaco
Mongolia
Montenegro
Montserrat
Morocco
Mozambique
Myanmar
Namibia
Nauru
Nepal
Netherlands Antilles
New Caledonia
New Zealand
Nicaragua
Niger
Nigeria
Niue
Norfolk Island
North Macedonia
Northern Mariana Islands
Oman
Pakistan
Palau
Palestine
Panama
Papua New Guinea
Paraguay
Peru
Philippines
Pitcairn
Poland
Portugal
Puerto Rico
Qatar
Reunion
Romania
Russian Federation
Rwanda
Saint Bartholemy
Saint Kitts And Nevis
Saint Lucia
Saint Martin
Saint Vincent And The Grenadines
Samoa
San Marino
Sao Tome And Principe
Saudi Arabia
Senegal
Serbia
Seychelles
Sierra Leone
Sint Maarten
Slovakia
Slovenia
Solomon Islands
South Africa
South Georgia and the South Sandwich Islands
South Sudan
Sri Lanka
St. Helena
St. Pierre And Miquelon
Suriname
Svalbard And Jan Mayen Islands
Sweden
Switzerland
Taiwan
Tajikistan
Tanzania, United Republic Of
Thailand
Togo
Tokelau
Tonga
Trinidad And Tobago
Tunisia
Turkey
Turkmenistan
Turks And Caicos Islands
Tuvalu
Uganda
Ukraine
United Arab Emirates
United States Minor Outlying Islands
Uruguay
Uzbekistan
Vanuatu
Vatican City State
Venezuela
Vietnam
Virgin Islands (British)
Virgin Islands (U.S.)
Wallis And Futuna Islands
Western Sahara
Yemen
Zambia
Zimbabwe

By providing this information, you agree to the processing of your personal data by SANS as described in our Privacy Policy.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Recommended Training

  • SEC450: Blue Team Fundamentals: Security Operations and Analysis™
  • SEC497: Practical Open-Source Intelligence (OSINT)™
  • SEC598: Security Automation for Offense, Defense, and Cloud™

Tags:
  • Artificial Intelligence (AI)
  • Security Awareness

Related Content

Blog
ICS - Blog - ICS_OT Cybersecurity & AI- Considerations for Now and the Future - Part 2_340 x 340.jpg
Industrial Control Systems Security, Artificial Intelligence (AI)
October 16, 2024
ICS/OT Cybersecurity & AI: Considerations for Now and the Future (Part II)
Integrating AI into ICS/OT cybersecurity and engineering processes presents opportunities for enhanced efficiency, resiliency, and safety.
DeanParsons_340x340.png
Dean Parsons
read more
Blog
AI Blog.png
Artificial Intelligence (AI)
September 9, 2024
A Visual Summary of SANS AI Cybersecurity Summit 2024
Check out these graphic recordings created in real-time throughout the event for SANS AI Cybersecurity Summit 2024
No Headshot Available
Alison Kim
read more
Blog
SSA - Blog - Tackling Modern Human Risks in Cybersecurity - Verizoin DBIR 2024_340 x 340.jpg
Security Awareness
May 16, 2024
Tackling Modern Human Risks in Cybersecurity: Insights from the Verizon DBIR 2024
The Verizon Data Breach Incident Report (VZ DBIR) is one of the security industries most respected annual reports on risk.
370x370_Lance-Spitzner.jpg
Lance Spitzner
read more
  • Company
  • Mission
  • Instructors
  • About
  • FAQ
  • Press
  • Contact Us
  • Careers
  • Policies
  • Training Programs
  • Work Study
  • Academies & Scholarships
  • Public Sector Partnerships
  • Law Enforcement
  • SkillsFuture Singapore
  • Degree Programs
  • Get Involved
  • Join the Community
  • Become an Instructor
  • Become a Sponsor
  • Speak at a Summit
  • Join the CISO Network
  • Award Programs
  • Partner Portal
Subscribe to SANS Newsletters
Receive curated news, vulnerabilities, & security awareness tips
United States
Canada
United Kingdom
Spain
Belgium
Denmark
Norway
Netherlands
Australia
India
Japan
Singapore
Afghanistan
Aland Islands
Albania
Algeria
American Samoa
Andorra
Angola
Anguilla
Antarctica
Antigua and Barbuda
Argentina
Armenia
Aruba
Austria
Azerbaijan
Bahamas
Bahrain
Bangladesh
Barbados
Belarus
Belize
Benin
Bermuda
Bhutan
Bolivia
Bonaire, Sint Eustatius, and Saba
Bosnia And Herzegovina
Botswana
Bouvet Island
Brazil
British Indian Ocean Territory
Brunei Darussalam
Bulgaria
Burkina Faso
Burundi
Cambodia
Cameroon
Cape Verde
Cayman Islands
Central African Republic
Chad
Chile
China
Christmas Island
Cocos (Keeling) Islands
Colombia
Comoros
Cook Islands
Costa Rica
Cote D'ivoire
Croatia (Local Name: Hrvatska)
Curacao
Cyprus
Czech Republic
Democratic Republic of the Congo
Djibouti
Dominica
Dominican Republic
East Timor
Ecuador
Egypt
El Salvador
Equatorial Guinea
Eritrea
Estonia
Eswatini
Ethiopia
Falkland Islands (Malvinas)
Faroe Islands
Fiji
Finland
France
French Guiana
French Polynesia
French Southern Territories
Gabon
Gambia
Georgia
Germany
Ghana
Gibraltar
Greece
Greenland
Grenada
Guadeloupe
Guam
Guatemala
Guernsey
Guinea
Guinea-Bissau
Guyana
Haiti
Heard And McDonald Islands
Honduras
Hong Kong
Hungary
Iceland
Indonesia
Iraq
Ireland
Isle of Man
Israel
Italy
Jamaica
Jersey
Jordan
Kazakhstan
Kenya
Kiribati
Korea, Republic Of
Kosovo
Kuwait
Kyrgyzstan
Lao People's Democratic Republic
Latvia
Lebanon
Lesotho
Liberia
Liechtenstein
Lithuania
Luxembourg
Macau
Madagascar
Malawi
Malaysia
Maldives
Mali
Malta
Marshall Islands
Martinique
Mauritania
Mauritius
Mayotte
Mexico
Micronesia, Federated States Of
Moldova, Republic Of
Monaco
Mongolia
Montenegro
Montserrat
Morocco
Mozambique
Myanmar
Namibia
Nauru
Nepal
Netherlands Antilles
New Caledonia
New Zealand
Nicaragua
Niger
Nigeria
Niue
Norfolk Island
North Macedonia
Northern Mariana Islands
Oman
Pakistan
Palau
Palestine
Panama
Papua New Guinea
Paraguay
Peru
Philippines
Pitcairn
Poland
Portugal
Puerto Rico
Qatar
Reunion
Romania
Russian Federation
Rwanda
Saint Bartholemy
Saint Kitts And Nevis
Saint Lucia
Saint Martin
Saint Vincent And The Grenadines
Samoa
San Marino
Sao Tome And Principe
Saudi Arabia
Senegal
Serbia
Seychelles
Sierra Leone
Sint Maarten
Slovakia
Slovenia
Solomon Islands
South Africa
South Georgia and the South Sandwich Islands
South Sudan
Sri Lanka
St. Helena
St. Pierre And Miquelon
Suriname
Svalbard And Jan Mayen Islands
Sweden
Switzerland
Taiwan
Tajikistan
Tanzania, United Republic Of
Thailand
Togo
Tokelau
Tonga
Trinidad And Tobago
Tunisia
Turkey
Turkmenistan
Turks And Caicos Islands
Tuvalu
Uganda
Ukraine
United Arab Emirates
United States Minor Outlying Islands
Uruguay
Uzbekistan
Vanuatu
Vatican City State
Venezuela
Vietnam
Virgin Islands (British)
Virgin Islands (U.S.)
Wallis And Futuna Islands
Western Sahara
Yemen
Zambia
Zimbabwe

By providing this information, you agree to the processing of your personal data by SANS as described in our Privacy Policy.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
  • Privacy Policy
  • Terms and Conditions
  • Do Not Sell/Share My Personal Information
  • Contact
  • Careers
© 2025 The Escal Institute of Advanced Technologies, Inc. d/b/a SANS Institute. Our Terms and Conditions detail our trademark and copyright rights. Any unauthorized use is expressly prohibited.
  • Twitter
  • Facebook
  • Youtube
  • LinkedIn