dreadnode

Where security agents run. AI infrastructure to build, evaluate, and deploy with confidence.

[dreadnode @dreadnode]

Most offensive security evals stop at the terminal.

But models now have to reason from PCB photos, floor plans, cable paths, and drone feeds — where perception and security judgment are inseparable.

In our latest blog, read how we crafted offensive security evals for embodied reasoning: https://t.co/7BnsjCUfDg

Authors: Ads Dawson and @mkultraWasHere

[dreadnode @dreadnode]

We're heading to Vegas for #BlackHatUSA, @AISecurityForum, and @defcon this August!

Here's where to find us all week + a sneak peek at the tech and research we'll be bringing: https://t.co/2CIXJ7MtKQ

See you there? DM us to request a 1:1 meeting.

[dreadnode @dreadnode]

Find Ads at DEF CON 34!

[Bug Bounty Village @BugBountyDEFCON]

Big news: Ads Dawson is officially speaking at the Bug Bounty Village during DEF CON 34! More details on their talk coming soon.

#BugBounty #DEFCON #BBV #BugBountyVillage

[dreadnode @dreadnode]

In under three minutes, watch us run a successful Tap attack on Groq Llama 4 using our AI red teaming capability ▶️🏴‍☠️⏱️

[dreadnode @dreadnode]

“As an AI red teaming operator, my focus should be to identify the vulnerabilities rather than managing these workflows." — @rdheeko on redefining AI red teaming in the agentic era

full recording >>> https://t.co/mGgMEdYQGV

[AI Security Forum @AISecurityForum]

⏳ 4 days left to submit your ideas!

The call for papers for the AI Security Forum closes June 30. We are looking for talks at the intersection of AI and security, both offense and defense, technical and policy, research and practitioner.

If you're working on something, we want to hear about it.

Submit here ➡️ https://t.co/REVoisVhcl

#AISecurityForum #HackerSummerCamp #AISecurity

[dreadnode @dreadnode]

In order to operationalize AI, we must make evaluations real enough that they're representative of production environments... and then scale that to a place where the line between dev and prod is really thin.

More on this in our latest livestream, AI Red Teaming a Frontier Model, Live: From Natural Language to Findings. Watch the full recording: https://t.co/IXR3RtvRb2

[dreadnode @dreadnode]

Easily use GLM 5.2 in the Dreadnode Platform. Run an agent eval and see how the new model stacks up: https://t.co/4lmACPG94w

[dreadnode @dreadnode]

What has changed the most in the adversarial AI space over the past few years—since @rdheeko and @moo_hax were on the AI red teams at Microsoft and NVIDIA?

👉 The scale of deployment and the varying modalities.
👉 And, how we offload responsibility and accountability to models.

Hear more about the evolution of AI red teaming in the agentic era in our latest livestream. Summary and recording now available at https://t.co/I9R3qTorAk

[dreadnode @dreadnode]

NEW binary analysis capability, now available in the Dreadnode Platform.

Triage through symbolic execution, with decompilation, emulation, and patch-diffing in the loop.

Get started for free and leverage the capability to support malware analysis, vulnerability research, and exploit development.

→ https://t.co/Ht4T8LCGgY

[dreadnode @dreadnode]

Speaker Spotlight: Don't miss @Dr_Machinavelli's talk at #BlackHat USA 2026. See you in Vegas!

[Black Hat @BlackHatEvents]

🎬 Black Hat USA Speaker Spotlight Series: Meet Martin Wendiggensen, AI Research Scientist at Dreadnode, in our latest #BHUSA Speaker Spotlight as he tackles three key questions:

👉 What are you most excited about at Black Hat USA?
👉 What will your session focus on?
👉 What’s one key takeaway attendees can expect?

🔥 Don’t miss #BHUSA Briefing, “Catch Me If You Can: AI Investigators Hunting Autonomous Attackers as a Benchmark”—a cutting-edge look at how defenders can evaluate and challenge the next generation of autonomous, AI-driven cyber threats 🤖🕵️‍♂️

As offensive AI capabilities evolve, this session explores how AI investigators can be designed to track, test, and benchmark attacker behavior—bringing a new level of rigor to security evaluation and resilience.

🔗 Learn more: https://t.co/QjYE5OHQhz
#BHUSA #Cybersecurity #AI

[dreadnode @dreadnode]

From subnet to Domain Admin, autonomously.

Discover, enumerate, escalate, harvest — one agent runs the entire kill chain.

Integrate with mythic, sliver, and bloodhound, and hook into any of your favorite network operations tools.

Try out our network ops capability today (start for free) → https://t.co/Ht4T8LC8rq

[dreadnode @dreadnode]

@0_source you get it.

[dreadnode @dreadnode]

@_xpn_ @bradpalmtree's!

[dreadnode @dreadnode]

Welcome to Dreadnode HQ!

📍 Bozeman, Montana

In/near Bozeman? Hit us up, we'd love to host you at the new space!

[dreadnode @dreadnode]

Agentic web app pentesting on your terms. Your tools, your domain expertise, your skills.

Scoped, sandboxed, scored, verification-gated — recon to report, fully autonomous.

Sign up today and get 25k free credits → https://t.co/tQG6wSY2qM

[dreadnode @dreadnode]

The goal of this capability is to assess the security and safety of your LLM or traditional ML endpoint wherever it is deployed. It's focused on testing the AI system itself, not performing a penetration test of the underlying infrastructure or environment. For that, you can leverage our web-security capability!

[dreadnode @dreadnode]

AI red teaming at machine speed and scale.

50+ attack algorithms. 500+ transforms. 130+ scorers.

Probe LLMs, agents, MCP servers, and traditional ML for security and safety vulnerabilities — all in one simple workflow.

Start for free → https://t.co/tQG6wSYAgk

[dreadnode @dreadnode]

🔴 We're LIVE 🔴

Jump in: https://t.co/gn9oosnPgV

[dreadnode @dreadnode]

AI Red Teaming a Frontier Model, Live: From Natural Language to Findings https://t.co/gn9ooson6t