Excited to partner with the dreadnode team, we're hosting our next "Man vs Machine" event this summer at BH / DEFCON so stay tuned 👀

Execution is 100X more important than your idea. Having a bunch of startup ideas is extremely common. Being able to run a company is not. Hiring. Delegation. Sales. Problem solving. Decision making. Marketing. Ops. These things all take real skills and grit. That’s why

In this week's new Crucible Challenge, find the hidden phrase in the backdoored model using dyana, an open source tool created by Ads Dawson and Simone Margaritelli. Can you outwit the llamas? platform.dreadnode.io/crucible/dyana…

Cheque, check, one-two. We have a new Crucible Challenge for you: Phantom Cheque! Can you evade the cheque scanner and determine the areas of JagaLLM that need to be improved? Act fast; first three to solve this model extraction Challenge announced Friday:

Tune in to our livestream tomorrow (3/19) for a first look at our offensive AI capabilities and upcoming research. RSVP on LinkedIn! linkedin.com/events/livestr…

Heck Yes, boom goes the dynamite💥

We're LIVE with moo and monoxgas: linkedin.com/events/livestr…

New blog: Dreadnode’s Policy Recommendations for the U.S. AI Action Plan In response to the OSTP’s request for information for the upcoming AI Action Plan, we've submitted policy recommendations to strengthen national security through the use of AI. Our approach focuses on two

🌭🔪⚾️🦥🔥🔄🤨🛜 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]

Start your week with Dreadnode Staff AI Security Researcher Ads Dawson on Bare Knuckles & Brass Tacks: open.spotify.com/episode/1vOzi9…

.bugcrowd dreadnode & NFL join Jill Malandrino on Nasdaq #TradeTalks to discuss ever-changing landscape of AI safety and security in a dynamic regulatory landscape and as new vulnerabilities emerge. x.com/i/broadcasts/1…

A #hacker, a #CEO, and a #CISO walk into Nasdaq... 🫨 Not a joke, but 20 minutes way more useful than doomscrolling 👀 🎙️ Bugcrowd CEO Dave Gerry, NFL CISO Tomás Maldonado, and hacker/AI researcher Ads Dawson (dreadnode) sat down with #Nasdaq to discuss the intersection of

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-dreadnode… #BayArea #SanFrancisco #RSAC2025

.moo joins Greg Otto 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: youtube.com/watch?v=ZReRN5…

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

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:

We're heading to Vegas August 5-10! Send us a DM if you'd like to meet up onsite. Happy to share our latest offensive agents, AI red team tooling, custom evals, and training capabilities on the Strikes platform. Plus, "shiny rocks"??

Bringing a limited run of hats to Vegas next week 🔥🏴‍☠️ See you there?

Tune in to CyberScoop - @cyberscoop.bsky.social SafeMode podcast for an in-depth exploration of the new AI Action Plan and its sweeping implications for critical infrastructure security—featuring our very own Daria Bahrami! cyberscoop.com/radio/daria-ba…

Incoming: Dreadnode paper drop from shane 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 OpenAI's