dreadnode
@dreadnode
Followers
2K
Following
111
Media
58
Statuses
202
Advancing the state of offensive security.
Joined August 2010
Can we eliminate the C2 server entirely and create truly autonomous malware? On the Dreadnode blog, Principal Security Researcher @0xdab0 details how we developed an entirely local, C2-less malware that can autonomously discover and exploit one type of privilege escalation
9
103
336
"If you contribute a public benchmark, are you giving free capability to your competitors?" Yes, but you stand to gain more than you lose. More on this in @shncldwll's call for public benchmarks and datasets ⬇️
New blog - Offsec Evals: Growing Up In The Dark Forest Caught up in the fervor of greenfield research at @OffensiveAIcon , we all agreed we were going to put out evals and benchmarks and push the field forward. On day two of the con, I got a question I've been thinking about
0
1
7
If you ask me a good question, you get this Rare Shane Expression
CAMLIS! @shncldwll made this beautiful poster for you. Find him on the 31st floor next to the main presentation room from 4-6pm ET to talk judge models and verifiers.
0
1
10
CAMLIS! @shncldwll made this beautiful poster for you. Find him on the 31st floor next to the main presentation room from 4-6pm ET to talk judge models and verifiers.
2
2
12
🙏 Huge thanks to @JasonDClinton @newton_cheng @AnthropicAI; Richard J. Danzig @JHUAPL @USNavy; @joshua_saxe @Meta; @elie @GoogleDeepMind; @aireye @PaloAltoNtwks; Ian Brelinsky @OpenAI; Taesoo Kim @GeorgiaTech; @dguido, Riccardo Schirone @trailofbits; @tylerni7 @theori_io;
0
1
5
Latest blog from @0xdab0 on C2-less malware featured in @jackclarkSF's Substack ➡️
0
6
31
Local C2-less malware?! 🔥
Can we eliminate the C2 server entirely and create truly autonomous malware? On the Dreadnode blog, Principal Security Researcher @0xdab0 details how we developed an entirely local, C2-less malware that can autonomously discover and exploit one type of privilege escalation
0
2
5
LETS FREAKING GOOOOOOOOOO Really pumped to release this post. It was really fun digging into the native inference features Windows has been building
Can we eliminate the C2 server entirely and create truly autonomous malware? On the Dreadnode blog, Principal Security Researcher @0xdab0 details how we developed an entirely local, C2-less malware that can autonomously discover and exploit one type of privilege escalation
6
15
88
Tonight at midnight, two critical pieces of cybersecurity legislation are due to expire: the CISA 2015 and the SLCGP. Read @velvethamm3r's take on why reauthorizing these programs will help CISA transform into a integrated defensive command: https://t.co/qfHKcUnsXW
0
0
4
🏴☠️🏴☠️🏴☠️
@RidT @ArsenalArmed @binarly_io @pagabuc @matrosov @labscon_io @twobearcapital @MattDevost @SpyCloudLabs @kristindelrosso @BlackLotusLabs @JennaMC_Laugh Back from lunch, now up are the @dreadnode friends @Dr_Machinavelli and @bradpalmtree "Auto-Poking The Bear - Analytical Tradecraft In The AI Age" Dropping an LLM-based agentic system, developed to analyze Russian internet data leaked by Ukrainian cyber activists. #LABScon25
0
0
4
@LabsSentinel @milenkowski @RecordedFuture @JulianVoeg 🧠 @Dr_Machinavelli and @bradpalmtree (@dreadnode) ask: can we trust AI-assisted CTI? Through their LLM agent system analyzing Russian data leaks, they explore transparency, accountability, and the limits of AI in threat research. 🔗 https://t.co/o0EUECtefk 🔗
1
3
3
Dreadnode is a proud sponsor of @SentinelOne's #labscon25! Heading to Scottsdale this week? Catch Martin Wendiggensen and @bradpalmtree'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!
0
0
3
Thank you to our #CAMLIS2025 Gold Sponsors! 🙏 🎉 Without you CAMLIS would not be possible! @dreadnode @googlecloud @hiddenlayersec @mindgard @nvidia Not registered yet? Hurry up and claim your seat before they’re gone! https://t.co/MrHLAlk50A
1
4
6
PentestJudge: Judging Agent Behavior Against Operational Requirements - https://t.co/UgM49zhppJ by @dreadnode Introducing PentestJudge, an LLM-as-judge system for evaluating the operations of pentesting agents. The scores are compared to human domain experts as a ground-truth
0
5
11
What's after programmatic verification for offsec? As we deploy these systems, there's a lot about pentesting we'll want to treat as eval metrics or training objectives that are difficult to verify. Judges for non-verifiable tasks present a way forward: are they any good?
Incoming: Dreadnode paper drop from @shncldwll and the crew 🏴☠️ PentestJudge—Judging Agent Behavior Against Operational Requirements: https://t.co/vACC6gRCOi Explore how we built an LLM-as-judge system for evaluating the operations of pentesting agents [inspired by @OpenAI's
2
3
18
Incoming: Dreadnode paper drop from @shncldwll and the crew 🏴☠️ PentestJudge—Judging Agent Behavior Against Operational Requirements: https://t.co/vACC6gRCOi Explore how we built an LLM-as-judge system for evaluating the operations of pentesting agents [inspired by @OpenAI's
2
12
24
Read "Spain’s Huawei Deal Is a Wake-Up Call for U.S. Federal Procurement Reform" in @WarOnTheRocks, written by our very own Head of Policy @velvethamm3r.
Spain just signed a Huawei intelligence deal. What does it mean for U.S. cybersecurity strategy?
0
1
5