Lightnews — Scholar-powered news

Dreadnode @dreadnode.bsky.social · 24d

Dreadnode is a proud sponsor of @sentinelone.com's #labscon25!

Heading to Scottsdale this week? Catch @machinavelli.com and Brad Palm's talk, Auto-Poking the Bear—Analytical Tradecraft in the AI Age, on Thursday at 2pm MT.

Or, shoot us a DM to find time to meet up onsite!

Dreadnode @dreadnode.bsky.social · 24d

!!!

SentinelOne @sentinelone.com · 24d

🧠 @machinavelli.com and Brad Palm (@dreadnode.bsky.social) ask: can we trust AI-assisted CTI?

🔗 labscon.io/speakers/martin-wendiggensen
🔗 www.labscon.io/speakers/bra...

Dreadnode @dreadnode.bsky.social · Aug 6

Incoming: Dreadnode paper drop from Shane Caldwell and the crew.

PentestJudge—Judging Agent Behavior Against Operational Requirements: arxiv.org/abs/2508.02921

Explore how we built an LLM-as-judge system for evaluating the operations of pentesting agents (inspired by PaperBench).

1 1

Reposted by Dreadnode

velvethamm3r.bsky.social @velvethamm3r.bsky.social · Aug 1

✍ After talking AI Action Plan on @cyberscoop.bsky.social, wrote up @dreadnode.bsky.social thoughts on implementation ➡️ dreadnode.io/blog/five-ta...

‼️ While we debate frameworks, adversaries build AI attack capabilities. We need: evaluation ecosystems, red teaming, and procurement standards.

Evals: The Foundation for Autonomous Offensive Security

Dreadnode @dreadnode.bsky.social · Aug 1

In our latest blog, Shane Caldwell breaks down the process of creating a fully integrated, self-verifying agentic system that can do modern Windows Active Directory red team operations, without human interaction.

Read it here: dreadnode.io/blog/evals-t...

Learn how to build robust evaluations for autonomous red team agents that can perform Windows Active Directory operations. This blog covers action space design, programmatic verification, and measurin...

Building and Deploying Offensive Security Agents with Dreadnode

Dreadnode @dreadnode.bsky.social · Jul 25

Rise and shine! We're going live on Off By One with Stephen Sims this afternoon—meet us here at 11 AM PT: www.youtube.com/live/BzOmGw-...

YouTube video by Off By One Security

www.youtube.com

Dreadnode @dreadnode.bsky.social · Jun 26

At Military Cyber Professionals Association's #HammerCon event today? Hear Daria present on this topic at 2 PM in the Growing Innovations in Tech (GIT) track, or connect with the crew at our booth!

2

Dreadnode @dreadnode.bsky.social · Jun 26

In this edition of our From Compute to Congress policy blog series, Dreadnode Head of Policy Daria Bahrami explores how the TEST AI Act and red teaming standards can establish U.S. leadership in AI security: dreadnode.io/blog/from-co...

From Compute to Congress: Setting the Global Standard for AI Security

Daria explores how the TEST AI Act and red teaming standards can establish American leadership in AI security—a winning policy roadmap from Critical Effect DC 2025.

AI Red Teaming Case Study: Claude 3.7 Sonnet Solves the Turtle Challenge

Dreadnode @dreadnode.bsky.social · Jun 25

Read @rad-ads.bsky.social's breakdown of Claude's attack sequence against the notoriously hard-to-solve "turtle" challenge: dreadnode.io/blog/ai-red-...

See how Claude solved a notoriously difficult AI/ML CTF challenge, going beyond pattern matching to genuine problem-solving under adversarial conditions.

GitHub - vmsv/pivot2025-llmworkshop

Dreadnode @dreadnode.bsky.social · Jun 18

Introducing AIRTBench, an AI red teaming benchmark for evaluating language models’ ability to autonomously discover and exploit AI/ML security vulnerabilities.

Read the paper on arXiv: arxiv.org/abs/2506.14682

Open-source dataset and benchmark eval code repo: github.com/dreadnode/AI...

1 1 3

Dreadnode @dreadnode.bsky.social · May 20

Check out @machinavelli.com's "Build with AI" Rigging workshop from @pivotcon.bsky.social: github.com/vmsv/pivot20...

Contribute to vmsv/pivot2025-llmworkshop development by creating an account on GitHub.

github.com

2 5

Dreadnode @dreadnode.bsky.social · May 19

v3 of Rigging is out now. If you’re working with LLMs to build agents or run evaluations, check it out. We just added:

- Prompt caching for supported providers
- A unified tool system for function calling and fallbacks to xml/json parsing
- Native MCP integration

docs.dreadnode.io/open-source/...

docs.dreadnode.io

2 3

Dreadnode @dreadnode.bsky.social · May 15

Introducing our new blog series: "From Compute to Congress: Decoding AI Policy" by Dreadnode Head of Policy Daria Bahrami | Read the first post here: dreadnode.io/blog/from-co...

1 1

Dreadnode @dreadnode.bsky.social · May 8

Are manual or automated attacks more effective when attacking LLMs?

We found that automated approaches achieve significantly higher success rates (69.5%) compared to manual techniques (47.6%).

More insights on LLM attack execution methods here 👉 dreadnode.io/blog/the-aut...

Dreadnode @dreadnode.bsky.social · May 1

Strikes waitlist. Now open.

platform.dreadnode.io/waitlist/str...

[must have a Dreadnode account]

Dreadnode CEO Will Pearce on the ever-changing field of offensive AI security

Dreadnode @dreadnode.bsky.social · Apr 29

What's your take on the growing dominance of automated attacks and the implications for AI red teams? Here's ours— based on our analysis of 30 LLM challenges, attempted by 1,674 unique Crucible users, across 214,271 attack attempts: arxiv.org/abs/2504.19855

5 4

Dreadnode @dreadnode.bsky.social · Apr 21

@moohax.bsky.social joins @gregotto.bsky.social on CyberScoop's Safe Mode podcast! Tune in at the 10-minute mark for a discussion on how AI fits into the offensive security narrative and what it means for tooling and defenses: www.youtube.com/watch?v=ZReR...

YouTube video by CyberScoop

www.youtube.com

Dreadnode @dreadnode.bsky.social · Apr 16

Headed to RSA? Come meet the Dreadnode crew!

Whether you're looking for a private deep dive into our tech or want to hang out and talk offensive AI research, we'd love to connect.

Limited availability; Come and get it: calendly.com/tori-dreadno...

#BayArea #SanFrancisco #RSAC2025 #OffensiveAI

1 1

Dreadnode @dreadnode.bsky.social · Apr 9

Hey, we know that guy! Catch Dreadnode's @radads.bsky.social on NASDAQ #TradeTalks alongside @bugcrowd.com CEO
@davegerryjr.bsky.social and NFL CISO @tomasmald.bsky.social.

Tune in for a candid conversation on the intersection of AI and cybersecurity: www.nasdaq.com/videos/ever-...

www.nasdaq.com

1 2 7

Reposted by Dreadnode

Martin Wendiggensen @machinavelli.com · Apr 3

Will be talking about @dreadnode.bsky.social‘s great open-source rigging repo and how to build your own LLM workflows! Super excited!

PIVOTcon @pivotcon.bsky.social · Apr 3

Workshop 2: Building with AI - with Martin Wendiggensen @machinavelli.com and Vitor Ventura @vventura.bsky.social ,one of the best assorted CTI-AI builder duet on the market

✅retrieve local text data
✅LLM reasoning system with the tools for searches and analyses.
✅ AI agents

3/5

1 3

Dreadnode @dreadnode.bsky.social · Mar 26

🌭🔪⚾️🦥🔥🔄🤨🛜

8 new Challenges now live in Crucible: platform.dreadnode.io/crucible

These Challenges might look familiar… they first appeared at DEFCON 30 and were recently refactored for Crucible—enjoy! [Filter>Subject>DEFCON-30]

Dreadnode’s Policy Recommendations for the U.S. AI Action Plan

Dreadnode @dreadnode.bsky.social · Mar 26

New blog: Dreadnode’s Policy Recommendations for the U.S. AI Action Plan. Our response focuses on two critical strategies:

1️⃣ Leveraging AI to protect America
2️⃣ Attacking AI to find its limits

Read our complete response on the Dreadnode blog: dreadnode.io/blog/policy-...

Read Dreadnode’s AI policy recommendations for the U.S. AI Action Plan, which focuses on leveraging AI to protect America and attacking AI to find its limits.

Live Stream with Dreadnode Founders | LinkedIn

Dreadnode @dreadnode.bsky.social · Mar 19

We're LIVE: www.linkedin.com/events/lives...

📅 Date: Wednesday, March 19, 2025 | ⏰ Time: 10 AM PT / 1 PM ET Dreadnode, the company at the forefront of offensive AI research and development, recently announced its Series A funding announcement ...

www.linkedin.com