David J. Bianco (He/Him)

1.5K Followers
272 Following
498 Posts
Threat Hunting, Cyber Threat Intelligence, incident detection and response. SANS Certified Instructor. Special interest in helping newbies get into the field. He/Him
Bloghttps://detect-respond.blogspot.com
Twitter@DavidJBianco
Twittodonhttps://twittodon.com/share.php?t=DavidJBianco&[email protected]
Fave ShapePyramid
Look at all these YES voters!

Need a pager that renders Markdown and has code syntax highlighting for a bunch of languages? Try 'richless', now available via Homebrew for MacOS and Linux:

Just a simple "brew install DavidJBianco/tools/richless" to get started!

https://github.com/DavidJBianco/richless

I don't normally promote vendor talks, but this one will have some very practical ways to apply #AI to solve real #cybersecurity challenges, including my own agentic #ThreatHunting assistant.

https://www.ciscolive.com/emea/learn/session-catalog.html?search=CENAI-1325#/

My latest project was released this morning: the PEAK #ThreatHunting Assistant harnesses teams of AI agents to accelerate the process of preparing and planning your hunt.

Blog: https://blogs.cisco.com/security/introducing-peak-threat-hunting-assistant
GitHub: https://github.com/cisco-foundation-ai/PEAK-Assistant

Time to share a personal project I've been working on: MCP Remixer.

Remixer is an MCP server that proxies requests to other MCP servers. It allows you to:

- Aggregate multiple servers into one
- Add new tools or suppress existing tools
- Log every request from the MCP client and the servers' responses

https://github.com/DavidJBianco/MCP-Remixer

I did NOT see this coming.

1. Kryptos is fully solved (!!!!)
2. There's the threat of a lawsuit if the solution is made public

https://www.nytimes.com/2025/10/16/science/kryptos-cia-solution-sanborn-auction.html?unlocked_article_code=1.t08.Fb2g.wov0l-NgQKoE&smid=url-share

This is really cool research by one of my new teammates: examining the internal state of an #LLM can not only tell you what type of information it's processing, but is really good at detecting malicious or unsafe prompt injections.

It's like fMRI for LLMs.

https://www.linkedin.com/pulse/how-build-ai-firewall-using-foundation-sec-8b-instruct-fdtn-kzyaf

The video for my talk last month at the #Honeynet Project Workshop is now available.

"Hi Fidelity != Hi Effort: Meet DECEIVE, the AI-backed SSH Honeypot"

Thanks to the workshop organizers for having me!

https://www.youtube.com/watch?v=uxbzGcIegVU&t=7052s

Looking for a new gig as a #cybersecurity researcher? Want to figure out new ways to achieve better security outcomes then tell everyone how? Check out our opening on the #Splunk #SURGe team!

https://www.splunk.com/en_us/careers/jobs/sr-security-strategist-surge-32798.html

Sr. Security Strategist, SURGe | Splunk

Splunk