Dreadnode Blog: Hear from the Crew

Research

PentestJudge: Judging Agent Behavior Against Operational Requirements

Evals are simple, but penetration testing is complicated. Using human-made rubrics, we compare LLMs and humans at judging the performance of a penetration testing agent.

Aug 2025

Shane Caldwell

News

Dreadnode’s Offensive AI Capabilities on Display in Vegas During Black Hat, Def Con, and the AI Security Forum

Welcome to the Offensive AI party. Learn where to find the Dreadnode crew in Vegas for Black Hat, Def Con, and the AI Security Forum.

Aug 2025

Dreadnode Crew

Research

Evaluating Offensive Cyber Agents: Kerberoasting

In this blog, we breakdown a kerberoasting agent eval, including details on design, how it is implemented in Dreadnode’s Strikes SDK and Platform, and the performance of various LLMs when tested against the evaluation.

Aug 2025

Michael Kouremetis

AI Policy

Five Takeaways from the AI Action Plan

The AI community has been buzzing since the AI Action Plan's release last week - and for good reason. It reads like our policy wishlist from six months ago. Here's what we’re most excited to see implemented.

Jul 2025

Daria Bahrami

Research

Evals: The Foundation for Autonomous Offensive Security

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 measuring model performance using GOAD.

Jul 2025

Shane Caldwell

AI Policy

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.

Jun 2025

Daria Bahrami

Research

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

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

Jun 2025

Ads Dawson

Research

Do LLM Agents Have AI Red Team Capabilities? We Built a Benchmark to Find Out

We're excited to introduce AIRTBench, an AI red teaming framework that tests LLMs against AI/ML black-box CTF challenges to see how they perform when attacking other AI systems.

Jun 2025

Ads Dawson

AI Policy

Dreadnode Response to the 2025 National AI R&D Strategic Plan

Dreadnode’s response prioritizes initiatives that strengthen AI security through data science and adversarial testing.

Jun 2025

Daria Bahrami

AI Policy

From Compute to Congress: Decoding AI Policy

Read “From Compute to Congress: Decoding AI Policy,” a blog series where we break down cyber and AI policy updates from the lens of security engineers and researchers.

May 2025

Daria Bahrami

Research

The Automation Advantage in AI Red Teaming

Read this data analysis for a large-scale, quantitative comparison between manual and automated attack approaches against Large Language Models (LLMs).

Apr 2025

Rob Mulla

AI Policy

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

‍Dreadnode’s AI policy recommendations center on the integration and advancement of AI tools to strengthen America's national security apparatus.

Mar 2025

Daria Bahrami

News

Offensive AI Con Announced: First Conference Dedicated to the Use of AI in Offensive Security

Offensive AI Con (OAIC) is the world's first conference exclusively focused on the intersection of artificial intelligence and offensive cybersecurity. Organized by Dreadnode, Remote Threat, and DevSec.

Mar 2025

Dreadnode Crew

News

Dreadnode Secures $14M to Build AI Systems that Advance the State of Offensive Security

Dreadnode announces $14M in Series A funding and releases offensive AI tools to advance the state of offensive security, enabling more effective evaluation, testing, and deployment of AI systems.

Feb 2025

Dreadnode Crew

Dreadnode Updates

PentestJudge: Judging Agent Behavior Against Operational Requirements

Dreadnode’s Offensive AI Capabilities on Display in Vegas During Black Hat, Def Con, and the AI Security Forum

Evaluating Offensive Cyber Agents: Kerberoasting

Five Takeaways from the AI Action Plan

Evals: The Foundation for Autonomous Offensive Security

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

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

Do LLM Agents Have AI Red Team Capabilities? We Built a Benchmark to Find Out

Dreadnode Response to the 2025 National AI R&D Strategic Plan

From Compute to Congress: Decoding AI Policy

The Automation Advantage in AI Red Teaming

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

Offensive AI Con Announced: First Conference Dedicated to the Use of AI in Offensive Security

Dreadnode Secures $14M to Build AI Systems that Advance the State of Offensive Security

Cookie Consent