This Week's/Trending Posts

Hand-Picked/Curated Posts

Most Popular/Amcache

Hand-Picked/Weekly News

The Most/Recent Articles

Daily Blog #707: Surviving the Breach Podcast

A sleek and modern logo for a podcast titled 'Surviving The Breach' that explores the intersection of cybersecurity and business. The design features a central shield symbolizing protection, with circuitry patterns and network nodes embedded within. Behind the shield, a subtle outline of a business skyline suggests the business aspect, while glowing lines represent interconnected networks. The color scheme includes shades of blue, gray, and metallic tones to evoke themes of technology and security. The podcast name 'Surviving The Breach' is displayed in bold, futuristic font below the symbol, with a tagline space available. The overall design is professional, dynamic, and tech-savvy.

 

 Hello Reader,

                So today is Podcast day but I'm not going to post an episode today, instead I'm going to tell you about how the podcasts will proceed going forward. 


Podcasts:

1. Forensic Lunch - The overly technical, fully nerdy and all around good for you show that dives deep into the latest and greatest tools, research and techniques is coming back.

2. The Test Kitchen - The long form test videos will alternate with the lunch. The test kitchen is coming to the cloud and other places as we look to expand our knowledge where no forensicator has fully documented before. 

3. Surviving The Breach - Once a month Erik Harssema and I will be keeping things at a higher level. Surviving the Breach is a podcast devoted to helping business leaders deal with all of the things after the technical investigation is done. From materiality, privilege issues, auditors and boards we are going to talk through the all the things you need you (or your boss) to know when the worst has come to bear. 


I'm excited about all three of these podcasts as it will give me some variety on topics but I'm most excited to try my hand at speaking outside of the church of DFIR and seeing if we can reach the ears of the non technical. I've found that it's very easy for all of us to agree on technical facts, but getting those who control budgets and make decisions to be informed could possibly do the most good for those around them. 


The first episode will be published 1/13/25 and will be a discussion on determining whether or a breach is material or not for publicly traded companies.

Daily Blog #706: Using AI to help create better test evidence

 

 A visually engaging and creative illustration of an AI assisting a person in writing an interesting movie. The scene shows a human sitting at a desk with a laptop, surrounded by notes, sketches, and a storyboard. Beside them is a futuristic holographic AI assistant, resembling a humanoid figure made of glowing light and circuits, projecting ideas and images onto a floating screen. The setting is a cozy creative studio with warm lighting and inspirational elements like film reels and posters in the background. The overall mood is collaborative, innovative, and inspiring.

Hello Reader,

Two AI-related posts in a row might seem like a lot, but I’ve been incorporating AI into my research for the past couple of years, so it naturally comes up in my work. While I’m not quite ready to share what I’ve been doing recently with Cursor, an AI IDE, I do want to showcase how I’ve used AI to create better datasets for forensic testing.

Creating engaging datasets for others to learn from can be a challenge, particularly when it comes to adding interesting elements for people to discover. In the past, I relied on downloading random free ebooks or generating large files with random data. However, I wondered if AI could improve this process. So, I tried this prompt:

“Create a PowerShell script that will generate a series of files with names related to AI technologies and themed around projects called ‘AI Tacos’ and ‘AI Burritos.’ The script should create 100 files with random data to vary their sizes. The files should use popular extensions and avoid numbers in the names. Instead, include at least 30 unique terms commonly used in research and development.”

The AI-generated script worked perfectly. When executed, it created 100 files in my specified directory, each with randomized content and varied file extensions. The result, as shown in the screenshot below, added depth and realism to my sample datasets.

 


This kind of themed, random data is incredibly useful for making datasets feel more authentic. For example, I can create a new virtual hard drive (VHD), populate it with these files, and then focus on generating interactions that leave digital artifacts for forensic analysis.

If you’re looking to populate other types of content, AI can help there too. For instance, this prompt:

“Write 5 text messages between two friends named David Cowen and Matthew Seyer discussing what kind of tacos to have for lunch.”

Produced the following conversation:

David Cowen: Hey Matt, I'm thinking tacos for lunch today. You up for it?
Matthew Seyer: Absolutely, dude! I could eat tacos every day. Any idea what kind?
David Cowen: I'm torn between fish tacos and something spicy, like chipotle chicken. What do you think?
Matthew Seyer: Fish tacos would be great, but I’m kind of craving some good old barbacoa. How about we do both?
David Cowen: Perfect idea! Let’s split an order of each so we can try everything. I’ll meet you in 20.

I even took it a step further and used AI to craft detailed fictional personas. For example, I used this prompt:

“Create a background story for a fictional employee at a company called TacoCorp who has worked there for 10 years as an IT administrator. This person has been recruited by BurritoTown to steal secrets from TacoCorp. Provide motivations, names, and profiles for their boss, coworker, new boss at BurritoTown, and best friend who’s a local police officer. Include a CV, LinkedIn bio, and 10 social media posts detailing their life.”

The AI generated a detailed persona, including:

  • Name: Oliver Delgado
  • Email: [email protected]
  • Social Media Handle: @OllieTacoTech

Motivations for Betrayal:
Oliver felt undervalued and underpaid after a decade at TacoCorp. Financial pressure and resentment toward his boss pushed him to accept BurritoTown’s lucrative offer to steal TacoCorp’s secrets.

Supporting Characters:

  • Franklin Hoyt, a strict and demanding boss at TacoCorp.
  • Samantha Mills, a friendly coworker unaware of Oliver’s frustrations.
  • Grace Li, the ambitious new boss at BurritoTown.
  • Daniel Morales, Oliver’s loyal best friend and a local detective.

The AI even provided Oliver’s CV, LinkedIn bio, social media posts, and a detailed headshot description for his persona.

A hyper-realistic, professional LinkedIn headshot of a mid-30s Hispanic male named Oliver Delgado. He has short, neatly trimmed dark hair and a well-groomed beard. He is wearing a crisp light-blue button-down shirt with a subtle pattern, no tie, and has a natural, confident smile. The background is a softly blurred, neutral-toned studio setting, with professional, natural lighting highlighting his face. The framing is from the chest up, with an impeccable shallow depth of field that brings his facial features into sharp focus. The image appears indistinguishable from a high-quality photograph taken by a professional photographer, suitable for a LinkedIn profile.

This ability to quickly generate characters, scenarios, and realistic data allows me to focus on ensuring the technical accuracy of my work. AI tools are invaluable for filling in creative gaps and enhancing the realism of forensic datasets. Don’t underestimate how much they can help!